diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000000000000000000000000000000000000..52373fe24473b1aa44333d318f578ae6bf04b49b --- /dev/null +++ b/.gitattributes @@ -0,0 +1,36 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000000000000000000000000000000000000..85116e5283816d5f8aeafafaf4bc084d315cc10d --- /dev/null +++ b/README.md @@ -0,0 +1,58 @@ +--- +language: +- en +- zh +library_name: transformers +license: mit +pipeline_tag: text-generation +--- + +# GLM-4.6 + +
+ +
+

+ ๐Ÿ‘‹ Join our Discord community. +
+ ๐Ÿ“– Check out the GLM-4.6 technical blog, technical report(GLM-4.5), and Zhipu AI technical documentation. +
+ ๐Ÿ“ Use GLM-4.6 API services on Z.ai API Platform. +
+ ๐Ÿ‘‰ One click to GLM-4.6. +

+ +## Model Introduction + +Compared with GLM-4.5, **GLM-4.6** brings several key improvements: + +* **Longer context window:** The context window has been expanded from 128K to 200K tokens, enabling the model to handle more complex agentic tasks. +* **Superior coding performance:** The model achieves higher scores on code benchmarks and demonstrates better real-world performance in applications such as Claude Codeใ€Clineใ€Roo Code and Kilo Code, including improvements in generating visually polished front-end pages. +* **Advanced reasoning:** GLM-4.6 shows a clear improvement in reasoning performance and supports tool use during inference, leading to stronger overall capability. +* **More capable agents:** GLM-4.6 exhibits stronger performance in tool using and search-based agents, and integrates more effectively within agent frameworks. +* **Refined writing:** Better aligns with human preferences in style and readability, and performs more naturally in role-playing scenarios. + +We evaluated GLM-4.6 across eight public benchmarks covering agents, reasoning, and coding. Results show clear gains over GLM-4.5, with GLM-4.6 also holding competitive advantages over leading domestic and international models such as **DeepSeek-V3.1-Terminus** and **Claude Sonnet 4**. + +![bench](https://raw.githubusercontent.com/zai-org/GLM-4.5/refs/heads/main/resources/bench_glm46.png) + +## Inference + +**Both GLM-4.5 and GLM-4.6 use the same inference method.** + +you can check our [github](https://github.com/zai-org/GLM-4.5) for more detail. + +## Recommended Evaluation Parameters + +For general evaluations, we recommend using a **sampling temperature of 1.0**. + +For **code-related evaluation tasks** (such as LCB), it is further recommended to set: + +- `top_p = 0.95` +- `top_k = 40` + + +## Evaluation + +- For tool-integrated reasoning, please refer to [this doc](https://github.com/zai-org/GLM-4.5/blob/main/resources/glm_4.6_tir_guide.md). +- For search benchmark, we design a specific format for searching toolcall in thinking mode to support search agent, please refer to [this](https://github.com/zai-org/GLM-4.5/blob/main/resources/trajectory_search.json). for the detailed template. diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000000000000000000000000000000000000..41478957aca7a04b7321022e7d1f73de5badd995 --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1,103 @@ +[gMASK] +{%- if tools -%} +<|system|> +# Tools + +You may call one or more functions to assist with the user query. + +You are provided with function signatures within XML tags: + +{% for tool in tools %} +{{ tool | tojson(ensure_ascii=False) }} +{% endfor %} + + +For each function call, output the function name and arguments within the following XML format: +{function-name} +{arg-key-1} +{arg-value-1} +{arg-key-2} +{arg-value-2} +... +{%- endif -%} +{%- macro visible_text(content) -%} + {%- if content is string -%} + {{- content }} + {%- elif content is iterable and content is not mapping -%} + {%- for item in content -%} + {%- if item is mapping and item.type == 'text' -%} + {{- item.text }} + {%- elif item is string -%} + {{- item }} + {%- endif -%} + {%- endfor -%} + {%- else -%} + {{- content }} + {%- endif -%} +{%- endmacro -%} +{%- set ns = namespace(last_user_index=-1) %} +{%- for m in messages %} + {%- if m.role == 'user' %} + {% set ns.last_user_index = loop.index0 -%} + {%- endif %} +{%- endfor %} +{% for m in messages %} +{%- if m.role == 'user' -%}<|user|> +{{ visible_text(m.content) }} +{{- '/nothink' if (enable_thinking is defined and not enable_thinking and not visible_text(m.content).endswith("/nothink")) else '' -}} +{%- elif m.role == 'assistant' -%} +<|assistant|> +{%- set reasoning_content = '' %} +{%- set content = visible_text(m.content) %} +{%- if m.reasoning_content is string %} + {%- set reasoning_content = m.reasoning_content %} +{%- else %} + {%- if '' in content %} + {%- set reasoning_content = content.split('')[0].rstrip('\n').split('')[-1].lstrip('\n') %} + {%- set content = content.split('')[-1].lstrip('\n') %} + {%- endif %} +{%- endif %} +{%- if loop.index0 > ns.last_user_index and reasoning_content -%} +{{ '\n' + reasoning_content.strip() + ''}} +{%- else -%} +{{ '\n' }} +{%- endif -%} +{%- if content.strip() -%} +{{ '\n' + content.strip() }} +{%- endif -%} +{% if m.tool_calls %} +{% for tc in m.tool_calls %} +{%- if tc.function %} + {%- set tc = tc.function %} +{%- endif %} +{{ '\n' + tc.name }} +{% set _args = tc.arguments %} +{% for k, v in _args.items() %} +{{ k }} +{{ v | tojson(ensure_ascii=False) if v is not string else v }} +{% endfor %} +{% endfor %} +{% endif %} +{%- elif m.role == 'tool' -%} +{%- if m.content is string -%} +{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %} + {{- '<|observation|>' }} +{%- endif %} +{{- '\n\n' }} +{{- m.content }} +{{- '\n' }} +{%- else -%} +<|observation|>{% for tr in m.content %} + + +{{ tr.output if tr.output is defined else tr }} +{% endfor -%} +{% endif -%} +{%- elif m.role == 'system' -%} +<|system|> +{{ visible_text(m.content) }} +{%- endif -%} +{%- endfor -%} +{%- if add_generation_prompt -%} + <|assistant|>{{- '\n' if (enable_thinking is defined and not enable_thinking) else '' -}} +{%- endif -%} \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000000000000000000000000000000000000..78978a509cc76da07da62953095abd1f887fbd2b --- /dev/null +++ b/config.json @@ -0,0 +1,43 @@ +{ + "architectures": [ + "Glm4MoeForCausalLM" + ], + "attention_bias": true, + "attention_dropout": 0.0, + "pad_token_id": 151329, + "eos_token_id": [ + 151329, + 151336, + 151338 + ], + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 5120, + "partial_rotary_factor": 0.5, + "initializer_range": 0.02, + "intermediate_size": 12288, + "max_position_embeddings": 202752, + "model_type": "glm4_moe", + "moe_intermediate_size": 1536, + "norm_topk_prob": true, + "num_attention_heads": 96, + "n_group": 1, + "topk_group": 1, + "n_routed_experts": 160, + "n_shared_experts": 1, + "routed_scaling_factor": 2.5, + "num_experts_per_tok": 8, + "first_k_dense_replace": 3, + "num_hidden_layers": 92, + "num_key_value_heads": 8, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 1000000, + "num_nextn_predict_layers": 1, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.54.0", + "use_cache": true, + "use_qk_norm": true, + "vocab_size": 151552 +} \ No newline at end of file diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..f51194759eb31dde6fbc75a28e3fb7036f68161a --- /dev/null +++ b/generation_config.json @@ -0,0 +1,11 @@ +{ + "_from_model_config": true, + "eos_token_id": [ + 151329, + 151336, + 151338 + ], + "pad_token_id": 151329, + "temperature": 1.0, + "transformers_version": "4.56.2" +} diff --git a/model-00001-of-00092.safetensors b/model-00001-of-00092.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a02b2526e9748a51ddc9ad8e57d4bc94442fd4af --- /dev/null +++ b/model-00001-of-00092.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e811e2ae0af3f8f5c78a4c44ef89a9f181e1b79e56d5860d6553b1f50918925a +size 2202060968 diff --git a/model-00002-of-00092.safetensors b/model-00002-of-00092.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8b69548cac28a4f272ff33c407b8325ea1693056 --- /dev/null +++ b/model-00002-of-00092.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:559c2c6c327cd224abf66411c7ee013d215578bb9561b0d7b9312f09c7332158 +size 650168352 diff --git a/model-00003-of-00092.safetensors b/model-00003-of-00092.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1b302d4e16d0bc90f4a3c603b8c922e3e735421e --- /dev/null +++ b/model-00003-of-00092.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f93e05487c6b84c6893ba3967dc05137d31cf4fcf5e52af284513b395d04b10 +size 650168352 diff --git a/model-00004-of-00092.safetensors b/model-00004-of-00092.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8e44cf3b55ba0e09837f55375b4829f886293768 --- /dev/null +++ b/model-00004-of-00092.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4013dad7c73dc6f653ca25d189fdcf43910f67d52816c80fe4d33535ecf28860 +size 7871313120 diff --git a/model-00005-of-00092.safetensors b/model-00005-of-00092.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c4e57b8d1585564caf1700ac084e068000cd54a9 --- /dev/null +++ b/model-00005-of-00092.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9892dea94d1a8988bcd0f7b84cfaffc512cf9d67009667f2d69fd9da612158e +size 7871313120 diff --git a/model-00006-of-00092.safetensors b/model-00006-of-00092.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7b89f0301ae1a6e673697a23ce5663cb905e648a --- /dev/null +++ b/model-00006-of-00092.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f24c50465ebae0f5313014a7ad7f6c3899c52a95e5a651a353c2766e4b4e7298 +size 7871313120 diff --git a/model-00007-of-00092.safetensors b/model-00007-of-00092.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..201ffb67a8029ebaff8977411fff31b3cd29092d --- /dev/null +++ b/model-00007-of-00092.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a5190f7eec27e00e65f49a92835c258552950c11e2a62b04255a00d176109a9 +size 7871313120 diff --git a/model-00008-of-00092.safetensors b/model-00008-of-00092.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..052049fc9b67b3c7abe84eeb78b8e8538a3b9cf6 --- /dev/null +++ b/model-00008-of-00092.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25028914f40903d33035641cd25b947437115f27d19fe097cef49a4699c05d0c +size 7871313120 diff --git a/model-00009-of-00092.safetensors b/model-00009-of-00092.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..cac572e68b3555db654da00f19f838215d90128b --- /dev/null +++ b/model-00009-of-00092.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ac318cfc36056c18fe0f320dcd407d85e8500de08884bef5d1b15f845a96646 +size 7871313120 diff --git a/model-00010-of-00092.safetensors b/model-00010-of-00092.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..61ba7fd61b50fe5a6e7edaa0bfd9bb8e574d46e7 --- /dev/null +++ b/model-00010-of-00092.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2fb398cc5157d66d2e8ef8f686a5df2bd4ac8a98265745256a3c66b588e7bf9d +size 7871313120 diff --git a/model-00011-of-00092.safetensors b/model-00011-of-00092.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f6b404eded073dd49ba3b1a6eb8e8789017a10f2 --- /dev/null +++ b/model-00011-of-00092.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:629bab852e515c3cea074e88db1f72e37ca27bb5b2af456af2e3eae26e45d66a +size 7871313616 diff --git a/model-00012-of-00092.safetensors b/model-00012-of-00092.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4b74fb4377bc2c8e1b20feed76d4d17296a255e7 --- /dev/null +++ b/model-00012-of-00092.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e643357d0afd3f1870a2df7fb05050e06a2816bbb0f6ef856da5bcf956ca604b +size 7871313616 diff --git a/model-00013-of-00092.safetensors b/model-00013-of-00092.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..bddd15911271b7bc94883523ca9460fab4ccb55d --- /dev/null +++ b/model-00013-of-00092.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec3175e3d7699175af6751a9ef126f65bd4269013ef9f6abc6e0b56cb9ac277c +size 7871313616 diff --git a/model-00014-of-00092.safetensors b/model-00014-of-00092.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ca06d80c516368e02fef398a2d97fd25e0b70181 --- /dev/null +++ b/model-00014-of-00092.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31fddd0d558a5e9b392980f25c5941b721d1b631f26664596fe00cc71651820e +size 7871313616 diff --git a/model-00015-of-00092.safetensors b/model-00015-of-00092.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6da0abc69477cb1436e69d8c1fc3d4182f778806 --- /dev/null +++ b/model-00015-of-00092.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cddeb04f13a56a6a781f44048bd0d8a250adf34b17c3c098173cc3fdd864419e +size 7871313616 diff --git a/model-00016-of-00092.safetensors b/model-00016-of-00092.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..139d4eaa0fce17573c58f2f15bcf39ce3b0fa917 --- /dev/null +++ b/model-00016-of-00092.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a6aa2577a4a8b5684ce6f4f49c1b4fb70aac88555b2c0367571efd328d6b9534 +size 7871313616 diff --git a/model-00017-of-00092.safetensors b/model-00017-of-00092.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7703aec30dada9820eeba5a1e0232bc675a94630 --- /dev/null +++ b/model-00017-of-00092.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00a194a3db95979ba04e0cdaddb85ca76cbb360612a2c550f04bea7ecd632acb +size 7871313616 diff --git a/model-00018-of-00092.safetensors b/model-00018-of-00092.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ef1464abad974aee1747219ef95b3348be4c671b --- /dev/null +++ b/model-00018-of-00092.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:29b6fd2128e8563cf20879d965b2c7b89ac1666edfcaef9332b1fbc5827ee2f0 +size 7871313616 diff --git a/model-00019-of-00092.safetensors b/model-00019-of-00092.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..bfd9f294cf86d55227b9b9bea20c63ac6fcc9f2b --- /dev/null +++ b/model-00019-of-00092.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc6c4804df6b1ea61d5b7bdf835e70f32d4df33d9a22d30be860b2cf71aae417 +size 7871313616 diff --git a/model-00020-of-00092.safetensors b/model-00020-of-00092.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9822f4d28fe60b5a520a8f2711581a2c168fea6b --- /dev/null +++ b/model-00020-of-00092.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0248883e585ab1d592d0589999037e1c3f299b10e20ece7d5c30bd77e375da1 +size 7871313616 diff --git a/model-00021-of-00092.safetensors b/model-00021-of-00092.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2378db0b960c2d3f9d09fbccc9a5f27565b64943 --- /dev/null +++ b/model-00021-of-00092.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8675a54477ce0675741a5fee9d062c0de78c3d0174e40a5d01de853ce53a6e4a +size 7871313616 diff --git a/model-00022-of-00092.safetensors b/model-00022-of-00092.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..12fe828c4228f906a1a328b2b38c37af5131481b --- /dev/null +++ b/model-00022-of-00092.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca1ae9a36b49cd3ecd25f8258b8d55ab0a1d1f7634fd273a0b548de5e9172acb +size 7871313616 diff --git a/model-00023-of-00092.safetensors b/model-00023-of-00092.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..84f47c1452e0b2136c6bedd156f3e0db3ee18b5e --- /dev/null +++ b/model-00023-of-00092.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d58920a549dbf9887b8e1229863d0cf62227c336191ba76089ae0af6f091d37 +size 7871313616 diff --git a/model-00024-of-00092.safetensors b/model-00024-of-00092.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2741a5eb414b581c1d55a05d47e29e44d7dc80c9 --- /dev/null +++ b/model-00024-of-00092.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f232bc262841b0edf63791096ea22b1ab3e76e7428f83d330387471ee29fe75c +size 7871313616 diff --git a/model-00025-of-00092.safetensors b/model-00025-of-00092.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..59669431eabb22442d62096a4b265b7065aceb2a --- /dev/null +++ b/model-00025-of-00092.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e57569bea34abe0023bc2183750ea37879deff0289f08d8e6e830515a7873558 +size 7871313616 diff --git a/model-00026-of-00092.safetensors b/model-00026-of-00092.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..55aecb95f70f127bc6a9605b1be6e157547fc8ca --- /dev/null +++ b/model-00026-of-00092.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41b3bd3383439b898faeeb5437a239a61721c4644b0a697439f47085310a98c9 +size 7871313616 diff --git a/model-00027-of-00092.safetensors b/model-00027-of-00092.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..79e276709602074f175114b64babbbe13273e822 --- /dev/null +++ b/model-00027-of-00092.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ebe5962e41760b4200dcaa85826f4767dad5290c263b89bba57b40c276a8789f +size 7871313616 diff --git a/model-00028-of-00092.safetensors b/model-00028-of-00092.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..47ddd23464b63b630fa55478eb9532b3eb23c0df --- /dev/null +++ b/model-00028-of-00092.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07577963a77cb7eb6f09f3d73d0d334c2211c216981c85eb7abdb03db2c340b9 +size 7871313616 diff --git a/model-00029-of-00092.safetensors b/model-00029-of-00092.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..532bef6b005ddc01a6daefeb99fec59cc27fb309 --- /dev/null +++ b/model-00029-of-00092.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d339dfc29d844e9aa92bde4efe3b23258ecd860ede53c2a986508e61c20a1a64 +size 7871313616 diff --git a/model-00030-of-00092.safetensors b/model-00030-of-00092.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9e34e2c0d77bb9ae0257eec07a39194963625c85 --- /dev/null +++ b/model-00030-of-00092.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48e67c5d8167ab23d033825f02e06c1a38143319ae15d4031a7387d30f910c2f +size 7871313616 diff --git a/model-00031-of-00092.safetensors b/model-00031-of-00092.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7134da9997ab6f414356f826d31e0ba0d0a62f1d --- /dev/null +++ b/model-00031-of-00092.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:768a839d45efba7a4334ac1c0e1b42babcf85d41e21c0da49756f3f2cc35bf41 +size 7871313616 diff --git a/model-00032-of-00092.safetensors b/model-00032-of-00092.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..23daf397a25862b2db381bb787db71a4e524dd9c --- /dev/null +++ b/model-00032-of-00092.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:596739c493b334a45eecd111b076924c4013aa4548afba895f2e6d9f0b9febed +size 7871313616 diff --git a/model-00033-of-00092.safetensors b/model-00033-of-00092.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7b786b0c84b75f6d180b3aa9349fc68d662e85fa --- /dev/null +++ b/model-00033-of-00092.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5462d2b82d87a28b3bd5a3263625f06aae9b1ddb20122793b8e16aa0848963e +size 7871313616 diff --git a/model-00034-of-00092.safetensors b/model-00034-of-00092.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..56f8b9cf8ffab0ccbbbbba9d72e21beff2ed5062 --- /dev/null +++ b/model-00034-of-00092.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:339a74144c5fe02a521675c7792e22d2b5ca66c1ef700eaac831d23086660670 +size 7871313616 diff --git a/model-00035-of-00092.safetensors b/model-00035-of-00092.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..459387de3bc510ee54587df0001ce37e2bdc4904 --- /dev/null +++ b/model-00035-of-00092.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2cddd87cb2c99a01502cedc7ea03e34baa3abb3256fdf69a0b100bde69e334c8 +size 7871313616 diff --git a/model-00036-of-00092.safetensors b/model-00036-of-00092.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3698dde6c714d2132d79184979f68841ccb66e9e --- /dev/null +++ b/model-00036-of-00092.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d530f1fe2348834c50a3b340dc359e173a5829f8334dfa5d0c33c0d8c6002a6 +size 7871313616 diff --git a/model-00037-of-00092.safetensors b/model-00037-of-00092.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6ff64daa90d632cc4d2b35bc1ce97e75b935df4e --- /dev/null +++ b/model-00037-of-00092.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa924217f71bde76d5ac2e6b214b9bfde70ad84cdde1f28b67e07100faeb6268 +size 7871313616 diff --git a/model-00038-of-00092.safetensors b/model-00038-of-00092.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..53ec0463904712362496232ef3080da55dad7ad2 --- /dev/null +++ b/model-00038-of-00092.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2d53da5652fed1a39ed583e8d76406c64fecc1abd9fd7bb9f4ac931224df1c6 +size 7871313616 diff --git a/model-00039-of-00092.safetensors b/model-00039-of-00092.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..519ef95ecfb4ac0aecc7b1219e159f02581c4319 --- /dev/null +++ b/model-00039-of-00092.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:712ef2e1ba038043d61157c09e137c9c208318e8420978238f1bc48b51467541 +size 7871313616 diff --git a/model-00040-of-00092.safetensors b/model-00040-of-00092.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c2e3478626065803fffb81fb65612ab1a3414b0e --- /dev/null +++ b/model-00040-of-00092.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:271106c38601a262ec8ecfe1319057a75eb0b3958761204c62bed09708fa552f +size 7871313616 diff --git a/model-00041-of-00092.safetensors b/model-00041-of-00092.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..74968c0727842cc11b4a03403cf97edefb2ae6da --- /dev/null +++ b/model-00041-of-00092.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a7b148aa720647b64138799df7b3a49d5a89f427dca4c1d5655f22bf9f83e42 +size 7871313616 diff --git a/model-00042-of-00092.safetensors b/model-00042-of-00092.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3f352ae302d2d5ff371040eab63e979438e65bb2 --- /dev/null +++ b/model-00042-of-00092.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:690961b65965bc559115df143cfb58ef9f0bbb39d86030825c0cc862f1c3adb2 +size 7871313616 diff --git a/model-00043-of-00092.safetensors b/model-00043-of-00092.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d374b31ea3df33ead5f2485a8327453c94daa313 --- /dev/null +++ b/model-00043-of-00092.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:194626c7568a6e8e252afc1b2e603c258879c91e7c691cfff5eaa152c86526b3 +size 7871313616 diff --git a/model-00044-of-00092.safetensors b/model-00044-of-00092.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..567e2667901b8c64c52627412ede1d075ac97235 --- /dev/null +++ b/model-00044-of-00092.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d62b81c57e5c8b16b12f3d19abd7ca638a92ff08561da136476bc1f5dd0d7e7 +size 7871313616 diff --git a/model-00045-of-00092.safetensors b/model-00045-of-00092.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3483217e0fe1ca3a3837ecb5f528017bf68d373d --- /dev/null +++ b/model-00045-of-00092.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19fb2b5f9bfaeba8cf4a7a2ac6e3cdbb227e8245cb905a7bfc37303a22f0f826 +size 7871313616 diff --git a/model-00046-of-00092.safetensors b/model-00046-of-00092.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e5c69548dc6c180f1f513f419460ccb420783b37 --- /dev/null +++ b/model-00046-of-00092.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8bb789ef9c2318b74c53f79fefcde10949feff78b2d6142cb692387cd9eabd54 +size 7871313616 diff --git a/model-00047-of-00092.safetensors b/model-00047-of-00092.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..043c8b118de5dfb8a7e7fd22648e5f3f89c7881c --- /dev/null +++ b/model-00047-of-00092.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72585bf5e925c79e9784b4cdc580cfa5f31b599642fd3e93c128b1572c5d32b2 +size 7871313616 diff --git a/model-00048-of-00092.safetensors b/model-00048-of-00092.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..42922470627f085c8460641d9c52c536d3076935 --- /dev/null +++ b/model-00048-of-00092.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:444dcd462d261532cdbe74214e7d2382c70334c7dc004dec12c4a68a078d986c +size 7871313616 diff --git a/model-00049-of-00092.safetensors b/model-00049-of-00092.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..806322f38d5bc7faf26072d8533ca509a9a6eee7 --- /dev/null +++ b/model-00049-of-00092.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0baa8e5ee558698e916323d2d5ebfa49b5de1440fb2d96fbffad19e308770ac +size 7871313616 diff --git a/model-00050-of-00092.safetensors b/model-00050-of-00092.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8624b6aa6398b618815bf1b499c0c457393f81a0 --- /dev/null +++ b/model-00050-of-00092.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c5b595d9373bb554fc2b48f46d80174e00ed421c9b59ed89bef0c3ab5b4d52d +size 7871313616 diff --git a/model-00051-of-00092.safetensors b/model-00051-of-00092.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b9cdd20f251ae2bec412b29a3d2b03ddea6d0cad --- /dev/null +++ b/model-00051-of-00092.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:42f4e0c9fa6e823bc8ad289e4c9f2f70ad745caba59c7aaf79dfa14b07944efa +size 7871313616 diff --git a/model-00052-of-00092.safetensors b/model-00052-of-00092.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1701c3583b26bedf498c8aa284624379994414f9 --- /dev/null +++ b/model-00052-of-00092.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea7559f8f72757d71ff9d1a2d2826a6ce412a6f5c28a44902fd315a0caa395e6 +size 7871313616 diff --git a/model-00053-of-00092.safetensors b/model-00053-of-00092.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1e0421e770b4d304598cd5c7695c944cc4e1ef35 --- /dev/null +++ b/model-00053-of-00092.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:afb106e8b3c09b81c33dc499d5af346e7289ed45a8be8c85058b83a452b13899 +size 7871313616 diff --git a/model-00054-of-00092.safetensors b/model-00054-of-00092.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..80e5623890678162107f9ff0b0cee0f9da657ae8 --- /dev/null +++ b/model-00054-of-00092.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:602654fff711aac235271938cd7f35a9f619281829477ea81b5e8e003a082847 +size 7871313616 diff --git a/model-00055-of-00092.safetensors b/model-00055-of-00092.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..37decf5c8c96be7c677d5be154a7dbda268bceb6 --- /dev/null +++ b/model-00055-of-00092.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2036275162aacdc6123daada2e59fdc5d306f2dce902ce415fca7f5d7bef9ad9 +size 7871313616 diff --git a/model-00056-of-00092.safetensors b/model-00056-of-00092.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..439f2500ea9de924d326011fe059965412acef53 --- /dev/null +++ b/model-00056-of-00092.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d669bc160d800f8624467c0c2da337b09e6ea998a332d4643d85509068a330fa +size 7871313616 diff --git a/model-00057-of-00092.safetensors b/model-00057-of-00092.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a34d608952b42badcc0a171985d5c4b5534eb8df --- /dev/null +++ b/model-00057-of-00092.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f0827368513647e94cf38c4c036bdd7e6160a958da092bc9132ddf81ac66f90 +size 7871313616 diff --git a/model-00058-of-00092.safetensors b/model-00058-of-00092.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4b0c1002619591da555edcd7a8b9d9560a1792f9 --- /dev/null +++ b/model-00058-of-00092.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:436ff9570f631c40f6a9d4bb9b2958c02f8da74e83ac3874746c6a7333eebfe7 +size 7871313616 diff --git a/model-00059-of-00092.safetensors b/model-00059-of-00092.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b2c9c9689716d67b4fa39f574b7466459584de0a --- /dev/null +++ b/model-00059-of-00092.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5e44053775342f68c1998db1ec8b579a4a793c159561dd68a05bc809b3062a2 +size 7871313616 diff --git a/model-00060-of-00092.safetensors b/model-00060-of-00092.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9af081114ead2c6649923c9870615aa9fe119ee8 --- /dev/null +++ b/model-00060-of-00092.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ada1d507de1d24612d93b052cd917715acc123b8b7f12c19fb820e5c908fe804 +size 7871313616 diff --git a/model-00061-of-00092.safetensors b/model-00061-of-00092.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a8abceaf17f4dd4e54d255ebb3c740d847fe3b5a --- /dev/null +++ b/model-00061-of-00092.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db150d1b7d2fa45dc13bfbf3cb1d51777db4ecf29c858a19b3314dc3c5cab7f9 +size 7871313616 diff --git a/model-00062-of-00092.safetensors b/model-00062-of-00092.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..25cfa2c5f674239d1eb87ee0ee60d2677d67fde6 --- /dev/null +++ b/model-00062-of-00092.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e32c5e24867f83bdfc80427f9d47c384115d8c870cc74d06dccb7dbb6eaadbd +size 7871313616 diff --git a/model-00063-of-00092.safetensors b/model-00063-of-00092.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2a6962ca657e9753e7d5aedc7dbd497299d626bd --- /dev/null +++ b/model-00063-of-00092.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90fab939bbff31124a800a31ed060e07d08758ed7f4b22f1647dba4aa5f84a39 +size 7871313616 diff --git a/model-00064-of-00092.safetensors b/model-00064-of-00092.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d663b76f6a3f41481b06c6b989e192b1d3f9e446 --- /dev/null +++ b/model-00064-of-00092.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50fb85490a55a3072babe3c8b3a4ceb8dd39bbdb993e7122679bd983cefba664 +size 7871313616 diff --git a/model-00065-of-00092.safetensors b/model-00065-of-00092.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3f09322eef8c8a532a29f400f24463fd9332ce20 --- /dev/null +++ b/model-00065-of-00092.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb5d32023d0dff37675a5900892f11450fbd46a81a8cc551f756765794ec0cd5 +size 7871313616 diff --git a/model-00066-of-00092.safetensors b/model-00066-of-00092.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..49e0c96643cc0ca71c4749fb534ea9576a45f0a2 --- /dev/null +++ b/model-00066-of-00092.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53bbe7b04af75a1fe180845537944842337113e0133ec3e165f8eba667966e1d +size 7871313616 diff --git a/model-00067-of-00092.safetensors b/model-00067-of-00092.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..98b138578db201b33462e151324ec93ba4b1feda --- /dev/null +++ b/model-00067-of-00092.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f47214e35f0991f3137a61dcea45a67783673e7825a741db0f164f2959d50d1b +size 7871313616 diff --git a/model-00068-of-00092.safetensors b/model-00068-of-00092.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4fba72da9242196fb47ba65906aef5c8b9fa3c60 --- /dev/null +++ b/model-00068-of-00092.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8457796efd9084c5b655120b19354f254908952faf3a1a35acbefbc2d425da9c +size 7871313616 diff --git a/model-00069-of-00092.safetensors b/model-00069-of-00092.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..179222b63707d495a3c7d52e632513c1b13b4c6a --- /dev/null +++ b/model-00069-of-00092.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e7b73a5c362be819b4f415e74b5d0a938072311a4ab02ee11c7e135ed5abc64 +size 7871313616 diff --git a/model-00070-of-00092.safetensors b/model-00070-of-00092.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..bfc338667e30e7903bbf50ec0fc13d85a349254d --- /dev/null +++ b/model-00070-of-00092.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f760ed87bb36684c84b511948caf88b26d106069f31bc027d852ab396d439c9 +size 7871313616 diff --git a/model-00071-of-00092.safetensors b/model-00071-of-00092.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..217bea3306ca2b5e192ee80e3704f9ede6abdf6f --- /dev/null +++ b/model-00071-of-00092.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ae7d886865cdfae7ffbda324336efcea2ffea2f51c5ab634d6181878eef3dc0 +size 7871313616 diff --git a/model-00072-of-00092.safetensors b/model-00072-of-00092.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..560686bf2e796800846483b76a97aedf9dc4c963 --- /dev/null +++ b/model-00072-of-00092.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d45652b52b5a37a16caa0651288493ac612415f479e2559ff67e40a6fda885e3 +size 7871313616 diff --git a/model-00073-of-00092.safetensors b/model-00073-of-00092.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..07faf7319d6bdd2d99166c19aafb2374ecf6a106 --- /dev/null +++ b/model-00073-of-00092.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68716a3261db26df7a26d35125ac2aaff44060ad5079e8150b88f537fa064fe0 +size 7871313616 diff --git a/model-00074-of-00092.safetensors b/model-00074-of-00092.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c5f105fe1fdecd5259394acd200a8b4601fe4925 --- /dev/null +++ b/model-00074-of-00092.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:754a31812f0d02e5dd19b1a76e62958944a3670b539735868647358e6286c3b1 +size 7871313616 diff --git a/model-00075-of-00092.safetensors b/model-00075-of-00092.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b8b411d6a89d971531b9fef886b57ac9b47c45f9 --- /dev/null +++ b/model-00075-of-00092.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eced6f7ad6bb62d86991cf1f3853af2cfd97a8c0b50c8cb37b3944e6be54f1d9 +size 7871313616 diff --git a/model-00076-of-00092.safetensors b/model-00076-of-00092.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..35e2cb688b0e189e56028e4d451daaeef2ed2e0c --- /dev/null +++ b/model-00076-of-00092.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0256e6bccf2771bf0b5b043b0e3653523bc5fe511ed88de4dc3b7678358fed3 +size 7871313616 diff --git a/model-00077-of-00092.safetensors b/model-00077-of-00092.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8b3e95860f6289ce558557e9a0ebf815a40d1566 --- /dev/null +++ b/model-00077-of-00092.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d2f73a6733de37abe0756b8d7c16869899e3d8a72ab1d5f07ee93d9a13f198bd +size 7871313616 diff --git a/model-00078-of-00092.safetensors b/model-00078-of-00092.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..93a76e92f4e3539d4a05253c4fad3eebbfee8017 --- /dev/null +++ b/model-00078-of-00092.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:42f89c8e7b4d92b79186b1bd939f79955c9d9eb2aa70c2e970b18b9ba96a90f8 +size 7871313616 diff --git a/model-00079-of-00092.safetensors b/model-00079-of-00092.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0b5102139312b76e50fea9fea9b78501d1794ca6 --- /dev/null +++ b/model-00079-of-00092.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88b43d8fb7a69ea34016144a1c01ab06ed71c747570fca222267c94179c8c7d9 +size 7871313616 diff --git a/model-00080-of-00092.safetensors b/model-00080-of-00092.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d4f1f843d8eb1bbac4199012afc81f26e9d60aec --- /dev/null +++ b/model-00080-of-00092.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4956edeac077d57fb51bd0f45ab3d2fb4c9b7e1aad44b11c6c10c2d9bb8a1e9b +size 7871313616 diff --git a/model-00081-of-00092.safetensors b/model-00081-of-00092.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3ba75406db8880bcace3d71443aa2ea5b1dfba35 --- /dev/null +++ b/model-00081-of-00092.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:396d314f57f5ea73de0ced68431c76da70b6bfe34ebcbfbb9f58426b58c804d6 +size 7871313616 diff --git a/model-00082-of-00092.safetensors b/model-00082-of-00092.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ab5891d745b0e46c3a53c6a52716ff4faa60cbf0 --- /dev/null +++ b/model-00082-of-00092.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:920c1883d2e3afc875e22a7e77709c9b3dcb7dee5ccb051ded2c56d11243cb1c +size 7871313616 diff --git a/model-00083-of-00092.safetensors b/model-00083-of-00092.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..98ee143ebfb28e607b640edec19a5ef6f051155f --- /dev/null +++ b/model-00083-of-00092.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d03d04dfe2ddbcbafe08398cffc3efd971ef5dcc543462d8b073b05d1f0fdc0f +size 7871313616 diff --git a/model-00084-of-00092.safetensors b/model-00084-of-00092.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d83a960cc9612d25d95158744f402b8e0b607753 --- /dev/null +++ b/model-00084-of-00092.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5965c07e27ab2dcc635d1cee1bc2bca315c0775d9799fb1233134bf5c25127c +size 7871313616 diff --git a/model-00085-of-00092.safetensors b/model-00085-of-00092.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f9320360d08f5801496a620a38a291bfb05ff175 --- /dev/null +++ b/model-00085-of-00092.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9bca0ac3b58f81f27d75d8b85f237970703a6b63523c022478727bf7037a7e79 +size 7871313616 diff --git a/model-00086-of-00092.safetensors b/model-00086-of-00092.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..edbde2f0f86ad6d6a9e14156491e329170fe53bf --- /dev/null +++ b/model-00086-of-00092.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf64b5e84ecdda12408ff891ac1e47ebf7748cf8514f410770c5bdea562d6a42 +size 7871313616 diff --git a/model-00087-of-00092.safetensors b/model-00087-of-00092.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..99c00e3c38d172bb1964563eff6c16e3933abc97 --- /dev/null +++ b/model-00087-of-00092.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:667171577fd04cd6e52170087e43cd84f91f16dcdc59bb26fd01f615df6bacdc +size 7871313616 diff --git a/model-00088-of-00092.safetensors b/model-00088-of-00092.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..20ebbdc852ffc63b92516cc198d0eff6f0aef86e --- /dev/null +++ b/model-00088-of-00092.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:508319e5995db40c52515c503b100044eb6a7163a18eea2a54c5dd70d6713bed +size 7871313616 diff --git a/model-00089-of-00092.safetensors b/model-00089-of-00092.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d11b7221ab4b68318f864ebc1b2260118efdb4a5 --- /dev/null +++ b/model-00089-of-00092.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb9d94974cb2ce6a4ce79c1909606198e15976fc42b07492c6f1549269923dc1 +size 7871313616 diff --git a/model-00090-of-00092.safetensors b/model-00090-of-00092.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..049d3a4a8da0951ab3b3f002d43b6285cd043eb7 --- /dev/null +++ b/model-00090-of-00092.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:942909838c33e494d35336fa8310fe50cd1bae2ab12d2ecea0ce554bd8ca85bc +size 7871313616 diff --git a/model-00091-of-00092.safetensors b/model-00091-of-00092.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e546232e51362fc89493ec069469d1a5e1fcaad8 --- /dev/null +++ b/model-00091-of-00092.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e94809fa57fa0801a2999d60c3e3d2361a1cd4ee9cdb705715381f008fc7c6b6 +size 7871313616 diff --git a/model-00092-of-00092.safetensors b/model-00092-of-00092.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8da000d9274c3b39000d6eea951f2c51475bfc09 --- /dev/null +++ b/model-00092-of-00092.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b06f796f99e203d6452089f9f808e4ee2521d6458849c8a893a8e4695c8178a6 +size 9423216672 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..a975956f950fb6aad290c1f50a49501868be322f --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,44696 @@ +{ + "metadata": { + "total_size": 352797829024 + }, + "weight_map": { + "model.embed_tokens.weight": "model-00001-of-00092.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00092.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00092.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00092.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00092.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00092.safetensors", + "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00092.safetensors", + "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00092.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00092.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00092.safetensors", + "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00092.safetensors", + "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00092.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00092.safetensors", + "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00092.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00092.safetensors", + "model.layers.1.input_layernorm.weight": "model-00002-of-00092.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00002-of-00092.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00092.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00002-of-00092.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00092.safetensors", + "model.layers.1.self_attn.k_norm.weight": "model-00002-of-00092.safetensors", + "model.layers.1.self_attn.k_proj.bias": "model-00002-of-00092.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00092.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00092.safetensors", + "model.layers.1.self_attn.q_norm.weight": "model-00002-of-00092.safetensors", + "model.layers.1.self_attn.q_proj.bias": "model-00002-of-00092.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00092.safetensors", + "model.layers.1.self_attn.v_proj.bias": "model-00002-of-00092.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00092.safetensors", + "model.layers.2.input_layernorm.weight": "model-00003-of-00092.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00003-of-00092.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00003-of-00092.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00003-of-00092.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00092.safetensors", + "model.layers.2.self_attn.k_norm.weight": "model-00003-of-00092.safetensors", + "model.layers.2.self_attn.k_proj.bias": "model-00003-of-00092.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00003-of-00092.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00003-of-00092.safetensors", + "model.layers.2.self_attn.q_norm.weight": "model-00003-of-00092.safetensors", + "model.layers.2.self_attn.q_proj.bias": "model-00003-of-00092.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00003-of-00092.safetensors", + "model.layers.2.self_attn.v_proj.bias": "model-00003-of-00092.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00003-of-00092.safetensors", + "model.layers.3.input_layernorm.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.0.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.0.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.0.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.1.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.1.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.1.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.10.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.10.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.10.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.100.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.100.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.100.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.101.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.101.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.101.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.102.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.102.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.102.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.103.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.103.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.103.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.104.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.104.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.104.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.105.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.105.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.105.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.106.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.106.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.106.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.107.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.107.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.107.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.108.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.108.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.108.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.109.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.109.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.109.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.11.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.11.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.11.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.110.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.110.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.110.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.111.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.111.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.111.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.112.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.112.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.112.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.113.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.113.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.113.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.114.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.114.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.114.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.115.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.115.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.115.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.116.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.116.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.116.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.117.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.117.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.117.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.118.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.118.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.118.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.119.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.119.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.119.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.12.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.12.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.12.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.120.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.120.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.120.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.121.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.121.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.121.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.122.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.122.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.122.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.123.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.123.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.123.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.124.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.124.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.124.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.125.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.125.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.125.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.126.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.126.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.126.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.127.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.127.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.127.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.128.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.128.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.128.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.129.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.129.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.129.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.13.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.13.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.13.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.130.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.130.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.130.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.131.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.131.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.131.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.132.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.132.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.132.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.133.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.133.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.133.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.134.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.134.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.134.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.135.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.135.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.135.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.136.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.136.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.136.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.137.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.137.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.137.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.138.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.138.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.138.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.139.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.139.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.139.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.14.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.14.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.14.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.140.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.140.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.140.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.141.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.141.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.141.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.142.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.142.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.142.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.143.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.143.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.143.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.144.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.144.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.144.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.145.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.145.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.145.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.146.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.146.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.146.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.147.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.147.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.147.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.148.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.148.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.148.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.149.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.149.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.149.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.15.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.15.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.15.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.150.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.150.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.150.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.151.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.151.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.151.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.152.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.152.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.152.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.153.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.153.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.153.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.154.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.154.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.154.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.155.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.155.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.155.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.156.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.156.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.156.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.157.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.157.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.157.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.158.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.158.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.158.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.159.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.159.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.159.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.16.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.16.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.16.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.17.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.17.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.17.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.18.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.18.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.18.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.19.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.19.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.19.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.2.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.2.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.2.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.20.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.20.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.20.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.21.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.21.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.21.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.22.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.22.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.22.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.23.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.23.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.23.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.24.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.24.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.24.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.25.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.25.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.25.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.26.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.26.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.26.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.27.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.27.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.27.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.28.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.28.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.28.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.29.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.29.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.29.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.3.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.3.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.3.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.30.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.30.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.30.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.31.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.31.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.31.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.32.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.32.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.32.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.33.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.33.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.33.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.34.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.34.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.34.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.35.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.35.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.35.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.36.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.36.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.36.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.37.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.37.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.37.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.38.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.38.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.38.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.39.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.39.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.39.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.4.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.4.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.4.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.40.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.40.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.40.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.41.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.41.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.41.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.42.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.42.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.42.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.43.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.43.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.43.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.44.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.44.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.44.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.45.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.45.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.45.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.46.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.46.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.46.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.47.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.47.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.47.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.48.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.48.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.48.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.49.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.49.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.49.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.5.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.5.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.5.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.50.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.50.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.50.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.51.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.51.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.51.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.52.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.52.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.52.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.53.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.53.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.53.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.54.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.54.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.54.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.55.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.55.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.55.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.56.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.56.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.56.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.57.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.57.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.57.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.58.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.58.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.58.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.59.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.59.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.59.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.6.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.6.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.6.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.60.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.60.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.60.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.61.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.61.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.61.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.62.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.62.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.62.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.63.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.63.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.63.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.64.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.64.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.64.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.65.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.65.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.65.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.66.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.66.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.66.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.67.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.67.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.67.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.68.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.68.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.68.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.69.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.69.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.69.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.7.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.7.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.7.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.70.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.70.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.70.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.71.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.71.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.71.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.72.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.72.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.72.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.73.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.73.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.73.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.74.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.74.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.74.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.75.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.75.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.75.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.76.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.76.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.76.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.77.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.77.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.77.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.78.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.78.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.78.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.79.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.79.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.79.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.8.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.8.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.8.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.80.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.80.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.80.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.81.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.81.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.81.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.82.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.82.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.82.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.83.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.83.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.83.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.84.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.84.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.84.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.85.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.85.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.85.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.86.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.86.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.86.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.87.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.87.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.87.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.88.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.88.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.88.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.89.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.89.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.89.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.9.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.9.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.9.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.90.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.90.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.90.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.91.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.91.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.91.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.92.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.92.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.92.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.93.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.93.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.93.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.94.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.94.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.94.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.95.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.95.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.95.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.96.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.96.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.96.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.97.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.97.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.97.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.98.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.98.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.98.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.99.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.99.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.experts.99.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.gate.e_score_correction_bias": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.gate.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.shared_experts.down_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.shared_experts.gate_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.mlp.shared_experts.up_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00004-of-00092.safetensors", + "model.layers.3.self_attn.k_norm.weight": "model-00004-of-00092.safetensors", + "model.layers.3.self_attn.k_proj.bias": "model-00004-of-00092.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.self_attn.q_norm.weight": "model-00004-of-00092.safetensors", + "model.layers.3.self_attn.q_proj.bias": "model-00004-of-00092.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.3.self_attn.v_proj.bias": "model-00004-of-00092.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00004-of-00092.safetensors", + "model.layers.4.input_layernorm.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.0.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.0.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.0.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.1.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.1.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.1.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.10.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.10.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.10.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.100.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.100.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.100.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.101.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.101.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.101.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.102.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.102.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.102.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.103.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.103.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.103.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.104.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.104.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.104.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.105.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.105.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.105.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.106.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.106.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.106.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.107.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.107.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.107.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.108.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.108.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.108.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.109.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.109.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.109.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.11.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.11.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.11.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.110.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.110.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.110.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.111.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.111.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.111.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.112.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.112.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.112.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.113.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.113.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.113.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.114.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.114.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.114.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.115.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.115.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.115.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.116.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.116.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.116.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.117.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.117.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.117.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.118.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.118.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.118.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.119.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.119.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.119.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.12.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.12.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.12.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.120.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.120.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.120.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.121.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.121.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.121.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.122.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.122.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.122.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.123.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.123.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.123.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.124.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.124.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.124.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.125.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.125.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.125.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.126.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.126.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.126.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.127.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.127.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.127.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.128.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.128.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.128.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.129.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.129.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.129.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.13.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.13.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.13.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.130.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.130.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.130.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.131.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.131.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.131.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.132.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.132.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.132.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.133.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.133.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.133.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.134.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.134.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.134.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.135.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.135.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.135.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.136.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.136.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.136.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.137.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.137.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.137.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.138.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.138.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.138.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.139.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.139.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.139.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.14.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.14.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.14.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.140.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.140.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.140.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.141.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.141.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.141.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.142.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.142.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.142.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.143.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.143.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.143.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.144.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.144.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.144.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.145.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.145.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.145.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.146.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.146.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.146.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.147.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.147.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.147.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.148.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.148.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.148.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.149.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.149.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.149.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.15.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.15.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.15.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.150.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.150.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.150.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.151.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.151.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.151.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.152.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.152.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.152.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.153.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.153.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.153.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.154.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.154.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.154.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.155.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.155.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.155.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.156.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.156.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.156.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.157.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.157.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.157.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.158.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.158.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.158.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.159.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.159.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.159.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.16.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.16.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.16.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.17.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.17.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.17.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.18.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.18.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.18.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.19.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.19.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.19.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.2.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.2.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.2.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.20.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.20.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.20.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.21.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.21.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.21.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.22.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.22.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.22.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.23.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.23.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.23.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.24.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.24.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.24.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.25.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.25.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.25.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.26.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.26.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.26.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.27.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.27.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.27.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.28.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.28.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.28.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.29.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.29.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.29.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.3.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.3.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.3.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.30.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.30.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.30.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.31.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.31.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.31.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.32.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.32.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.32.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.33.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.33.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.33.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.34.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.34.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.34.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.35.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.35.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.35.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.36.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.36.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.36.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.37.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.37.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.37.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.38.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.38.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.38.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.39.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.39.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.39.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.4.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.4.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.4.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.40.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.40.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.40.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.41.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.41.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.41.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.42.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.42.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.42.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.43.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.43.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.43.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.44.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.44.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.44.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.45.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.45.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.45.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.46.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.46.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.46.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.47.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.47.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.47.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.48.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.48.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.48.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.49.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.49.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.49.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.5.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.5.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.5.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.50.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.50.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.50.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.51.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.51.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.51.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.52.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.52.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.52.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.53.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.53.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.53.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.54.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.54.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.54.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.55.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.55.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.55.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.56.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.56.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.56.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.57.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.57.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.57.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.58.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.58.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.58.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.59.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.59.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.59.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.6.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.6.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.6.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.60.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.60.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.60.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.61.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.61.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.61.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.62.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.62.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.62.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.63.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.63.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.63.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.64.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.64.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.64.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.65.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.65.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.65.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.66.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.66.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.66.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.67.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.67.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.67.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.68.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.68.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.68.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.69.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.69.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.69.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.7.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.7.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.7.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.70.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.70.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.70.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.71.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.71.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.71.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.72.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.72.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.72.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.73.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.73.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.73.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.74.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.74.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.74.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.75.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.75.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.75.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.76.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.76.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.76.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.77.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.77.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.77.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.78.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.78.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.78.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.79.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.79.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.79.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.8.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.8.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.8.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.80.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.80.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.80.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.81.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.81.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.81.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.82.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.82.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.82.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.83.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.83.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.83.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.84.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.84.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.84.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.85.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.85.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.85.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.86.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.86.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.86.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.87.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.87.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.87.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.88.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.88.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.88.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.89.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.89.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.89.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.9.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.9.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.9.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.90.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.90.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.90.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.91.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.91.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.91.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.92.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.92.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.92.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.93.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.93.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.93.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.94.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.94.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.94.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.95.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.95.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.95.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.96.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.96.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.96.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.97.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.97.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.97.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.98.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.98.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.98.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.99.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.99.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.experts.99.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.gate.e_score_correction_bias": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.gate.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.shared_experts.down_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.shared_experts.gate_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.mlp.shared_experts.up_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00005-of-00092.safetensors", + "model.layers.4.self_attn.k_norm.weight": "model-00005-of-00092.safetensors", + "model.layers.4.self_attn.k_proj.bias": "model-00005-of-00092.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.self_attn.q_norm.weight": "model-00005-of-00092.safetensors", + "model.layers.4.self_attn.q_proj.bias": "model-00005-of-00092.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.4.self_attn.v_proj.bias": "model-00005-of-00092.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00005-of-00092.safetensors", + "model.layers.5.input_layernorm.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.0.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.0.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.0.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.1.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.1.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.1.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.10.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.10.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.10.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.100.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.100.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.100.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.101.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.101.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.101.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.102.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.102.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.102.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.103.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.103.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.103.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.104.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.104.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.104.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.105.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.105.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.105.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.106.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.106.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.106.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.107.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.107.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.107.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.108.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.108.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.108.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.109.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.109.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.109.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.11.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.11.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.11.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.110.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.110.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.110.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.111.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.111.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.111.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.112.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.112.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.112.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.113.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.113.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.113.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.114.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.114.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.114.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.115.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.115.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.115.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.116.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.116.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.116.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.117.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.117.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.117.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.118.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.118.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.118.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.119.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.119.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.119.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.12.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.12.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.12.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.120.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.120.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.120.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.121.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.121.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.121.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.122.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.122.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.122.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.123.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.123.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.123.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.124.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.124.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.124.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.125.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.125.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.125.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.126.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.126.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.126.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.127.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.127.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.127.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.128.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.128.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.128.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.129.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.129.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.129.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.13.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.13.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.13.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.130.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.130.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.130.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.131.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.131.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.131.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.132.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.132.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.132.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.133.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.133.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.133.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.134.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.134.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.134.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.135.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.135.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.135.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.136.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.136.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.136.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.137.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.137.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.137.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.138.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.138.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.138.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.139.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.139.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.139.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.14.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.14.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.14.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.140.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.140.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.140.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.141.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.141.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.141.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.142.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.142.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.142.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.143.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.143.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.143.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.144.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.144.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.144.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.145.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.145.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.145.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.146.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.146.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.146.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.147.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.147.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.147.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.148.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.148.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.148.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.149.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.149.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.149.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.15.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.15.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.15.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.150.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.150.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.150.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.151.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.151.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.151.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.152.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.152.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.152.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.153.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.153.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.153.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.154.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.154.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.154.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.155.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.155.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.155.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.156.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.156.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.156.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.157.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.157.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.157.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.158.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.158.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.158.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.159.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.159.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.159.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.16.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.16.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.16.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.17.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.17.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.17.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.18.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.18.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.18.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.19.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.19.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.19.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.2.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.2.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.2.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.20.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.20.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.20.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.21.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.21.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.21.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.22.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.22.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.22.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.23.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.23.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.23.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.24.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.24.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.24.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.25.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.25.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.25.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.26.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.26.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.26.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.27.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.27.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.27.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.28.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.28.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.28.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.29.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.29.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.29.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.3.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.3.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.3.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.30.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.30.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.30.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.31.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.31.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.31.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.32.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.32.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.32.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.33.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.33.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.33.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.34.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.34.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.34.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.35.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.35.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.35.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.36.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.36.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.36.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.37.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.37.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.37.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.38.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.38.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.38.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.39.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.39.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.39.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.4.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.4.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.4.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.40.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.40.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.40.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.41.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.41.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.41.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.42.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.42.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.42.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.43.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.43.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.43.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.44.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.44.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.44.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.45.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.45.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.45.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.46.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.46.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.46.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.47.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.47.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.47.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.48.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.48.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.48.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.49.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.49.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.49.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.5.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.5.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.5.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.50.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.50.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.50.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.51.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.51.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.51.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.52.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.52.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.52.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.53.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.53.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.53.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.54.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.54.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.54.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.55.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.55.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.55.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.56.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.56.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.56.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.57.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.57.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.57.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.58.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.58.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.58.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.59.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.59.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.59.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.6.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.6.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.6.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.60.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.60.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.60.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.61.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.61.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.61.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.62.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.62.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.62.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.63.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.63.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.63.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.64.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.64.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.64.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.65.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.65.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.65.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.66.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.66.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.66.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.67.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.67.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.67.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.68.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.68.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.68.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.69.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.69.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.69.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.7.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.7.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.7.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.70.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.70.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.70.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.71.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.71.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.71.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.72.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.72.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.72.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.73.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.73.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.73.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.74.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.74.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.74.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.75.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.75.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.75.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.76.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.76.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.76.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.77.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.77.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.77.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.78.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.78.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.78.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.79.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.79.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.79.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.8.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.8.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.8.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.80.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.80.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.80.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.81.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.81.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.81.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.82.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.82.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.82.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.83.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.83.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.83.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.84.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.84.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.84.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.85.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.85.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.85.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.86.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.86.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.86.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.87.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.87.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.87.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.88.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.88.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.88.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.89.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.89.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.89.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.9.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.9.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.9.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.90.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.90.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.90.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.91.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.91.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.91.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.92.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.92.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.92.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.93.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.93.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.93.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.94.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.94.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.94.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.95.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.95.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.95.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.96.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.96.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.96.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.97.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.97.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.97.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.98.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.98.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.98.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.99.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.99.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.experts.99.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.gate.e_score_correction_bias": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.gate.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.shared_experts.down_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.shared_experts.gate_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.mlp.shared_experts.up_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00006-of-00092.safetensors", + "model.layers.5.self_attn.k_norm.weight": "model-00006-of-00092.safetensors", + "model.layers.5.self_attn.k_proj.bias": "model-00006-of-00092.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.self_attn.q_norm.weight": "model-00006-of-00092.safetensors", + "model.layers.5.self_attn.q_proj.bias": "model-00006-of-00092.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.5.self_attn.v_proj.bias": "model-00006-of-00092.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00006-of-00092.safetensors", + "model.layers.6.input_layernorm.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.0.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.0.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.0.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.1.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.1.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.1.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.10.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.10.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.10.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.100.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.100.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.100.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.101.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.101.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.101.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.102.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.102.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.102.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.103.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.103.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.103.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.104.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.104.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.104.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.105.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.105.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.105.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.106.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.106.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.106.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.107.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.107.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.107.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.108.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.108.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.108.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.109.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.109.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.109.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.11.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.11.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.11.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.110.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.110.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.110.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.111.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.111.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.111.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.112.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.112.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.112.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.113.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.113.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.113.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.114.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.114.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.114.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.115.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.115.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.115.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.116.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.116.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.116.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.117.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.117.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.117.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.118.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.118.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.118.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.119.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.119.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.119.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.12.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.12.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.12.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.120.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.120.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.120.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.121.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.121.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.121.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.122.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.122.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.122.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.123.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.123.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.123.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.124.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.124.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.124.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.125.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.125.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.125.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.126.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.126.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.126.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.127.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.127.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.127.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.128.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.128.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.128.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.129.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.129.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.129.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.13.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.13.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.13.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.130.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.130.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.130.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.131.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.131.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.131.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.132.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.132.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.132.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.133.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.133.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.133.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.134.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.134.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.134.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.135.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.135.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.135.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.136.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.136.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.136.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.137.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.137.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.137.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.138.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.138.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.138.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.139.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.139.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.139.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.14.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.14.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.14.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.140.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.140.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.140.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.141.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.141.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.141.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.142.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.142.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.142.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.143.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.143.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.143.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.144.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.144.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.144.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.145.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.145.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.145.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.146.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.146.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.146.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.147.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.147.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.147.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.148.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.148.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.148.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.149.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.149.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.149.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.15.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.15.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.15.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.150.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.150.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.150.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.151.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.151.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.151.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.152.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.152.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.152.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.153.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.153.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.153.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.154.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.154.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.154.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.155.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.155.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.155.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.156.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.156.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.156.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.157.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.157.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.157.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.158.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.158.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.158.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.159.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.159.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.159.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.16.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.16.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.16.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.17.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.17.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.17.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.18.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.18.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.18.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.19.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.19.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.19.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.2.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.2.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.2.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.20.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.20.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.20.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.21.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.21.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.21.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.22.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.22.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.22.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.23.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.23.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.23.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.24.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.24.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.24.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.25.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.25.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.25.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.26.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.26.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.26.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.27.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.27.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.27.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.28.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.28.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.28.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.29.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.29.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.29.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.3.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.3.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.3.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.30.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.30.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.30.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.31.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.31.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.31.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.32.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.32.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.32.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.33.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.33.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.33.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.34.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.34.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.34.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.35.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.35.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.35.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.36.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.36.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.36.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.37.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.37.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.37.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.38.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.38.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.38.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.39.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.39.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.39.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.4.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.4.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.4.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.40.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.40.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.40.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.41.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.41.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.41.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.42.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.42.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.42.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.43.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.43.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.43.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.44.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.44.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.44.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.45.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.45.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.45.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.46.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.46.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.46.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.47.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.47.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.47.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.48.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.48.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.48.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.49.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.49.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.49.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.5.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.5.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.5.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.50.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.50.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.50.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.51.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.51.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.51.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.52.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.52.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.52.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.53.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.53.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.53.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.54.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.54.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.54.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.55.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.55.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.55.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.56.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.56.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.56.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.57.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.57.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.57.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.58.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.58.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.58.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.59.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.59.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.59.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.6.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.6.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.6.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.60.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.60.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.60.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.61.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.61.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.61.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.62.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.62.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.62.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.63.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.63.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.63.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.64.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.64.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.64.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.65.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.65.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.65.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.66.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.66.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.66.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.67.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.67.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.67.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.68.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.68.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.68.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.69.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.69.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.69.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.7.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.7.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.7.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.70.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.70.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.70.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.71.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.71.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.71.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.72.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.72.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.72.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.73.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.73.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.73.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.74.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.74.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.74.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.75.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.75.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.75.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.76.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.76.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.76.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.77.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.77.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.77.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.78.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.78.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.78.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.79.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.79.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.79.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.8.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.8.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.8.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.80.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.80.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.80.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.81.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.81.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.81.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.82.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.82.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.82.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.83.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.83.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.83.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.84.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.84.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.84.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.85.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.85.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.85.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.86.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.86.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.86.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.87.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.87.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.87.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.88.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.88.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.88.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.89.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.89.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.89.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.9.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.9.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.9.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.90.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.90.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.90.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.91.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.91.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.91.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.92.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.92.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.92.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.93.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.93.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.93.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.94.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.94.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.94.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.95.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.95.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.95.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.96.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.96.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.96.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.97.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.97.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.97.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.98.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.98.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.98.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.99.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.99.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.experts.99.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.gate.e_score_correction_bias": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.gate.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.shared_experts.down_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.shared_experts.gate_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.mlp.shared_experts.up_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00007-of-00092.safetensors", + "model.layers.6.self_attn.k_norm.weight": "model-00007-of-00092.safetensors", + "model.layers.6.self_attn.k_proj.bias": "model-00007-of-00092.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.self_attn.q_norm.weight": "model-00007-of-00092.safetensors", + "model.layers.6.self_attn.q_proj.bias": "model-00007-of-00092.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.6.self_attn.v_proj.bias": "model-00007-of-00092.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00007-of-00092.safetensors", + "model.layers.7.input_layernorm.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.0.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.0.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.0.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.1.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.1.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.1.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.10.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.10.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.10.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.100.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.100.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.100.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.101.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.101.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.101.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.102.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.102.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.102.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.103.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.103.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.103.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.104.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.104.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.104.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.105.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.105.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.105.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.106.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.106.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.106.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.107.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.107.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.107.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.108.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.108.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.108.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.109.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.109.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.109.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.11.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.11.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.11.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.110.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.110.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.110.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.111.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.111.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.111.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.112.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.112.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.112.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.113.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.113.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.113.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.114.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.114.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.114.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.115.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.115.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.115.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.116.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.116.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.116.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.117.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.117.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.117.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.118.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.118.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.118.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.119.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.119.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.119.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.12.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.12.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.12.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.120.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.120.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.120.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.121.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.121.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.121.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.122.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.122.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.122.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.123.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.123.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.123.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.124.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.124.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.124.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.125.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.125.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.125.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.126.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.126.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.126.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.127.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.127.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.127.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.128.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.128.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.128.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.129.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.129.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.129.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.13.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.13.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.13.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.130.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.130.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.130.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.131.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.131.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.131.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.132.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.132.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.132.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.133.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.133.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.133.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.134.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.134.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.134.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.135.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.135.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.135.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.136.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.136.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.136.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.137.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.137.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.137.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.138.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.138.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.138.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.139.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.139.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.139.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.14.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.14.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.14.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.140.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.140.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.140.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.141.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.141.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.141.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.142.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.142.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.142.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.143.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.143.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.143.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.144.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.144.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.144.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.145.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.145.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.145.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.146.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.146.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.146.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.147.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.147.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.147.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.148.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.148.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.148.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.149.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.149.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.149.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.15.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.15.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.15.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.150.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.150.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.150.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.151.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.151.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.151.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.152.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.152.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.152.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.153.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.153.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.153.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.154.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.154.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.154.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.155.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.155.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.155.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.156.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.156.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.156.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.157.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.157.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.157.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.158.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.158.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.158.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.159.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.159.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.159.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.16.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.16.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.16.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.17.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.17.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.17.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.18.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.18.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.18.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.19.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.19.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.19.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.2.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.2.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.2.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.20.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.20.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.20.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.21.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.21.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.21.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.22.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.22.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.22.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.23.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.23.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.23.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.24.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.24.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.24.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.25.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.25.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.25.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.26.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.26.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.26.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.27.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.27.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.27.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.28.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.28.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.28.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.29.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.29.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.29.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.3.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.3.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.3.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.30.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.30.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.30.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.31.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.31.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.31.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.32.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.32.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.32.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.33.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.33.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.33.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.34.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.34.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.34.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.35.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.35.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.35.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.36.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.36.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.36.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.37.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.37.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.37.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.38.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.38.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.38.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.39.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.39.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.39.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.4.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.4.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.4.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.40.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.40.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.40.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.41.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.41.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.41.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.42.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.42.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.42.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.43.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.43.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.43.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.44.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.44.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.44.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.45.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.45.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.45.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.46.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.46.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.46.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.47.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.47.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.47.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.48.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.48.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.48.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.49.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.49.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.49.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.5.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.5.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.5.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.50.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.50.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.50.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.51.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.51.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.51.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.52.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.52.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.52.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.53.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.53.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.53.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.54.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.54.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.54.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.55.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.55.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.55.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.56.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.56.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.56.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.57.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.57.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.57.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.58.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.58.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.58.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.59.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.59.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.59.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.6.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.6.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.6.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.60.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.60.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.60.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.61.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.61.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.61.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.62.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.62.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.62.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.63.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.63.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.63.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.64.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.64.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.64.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.65.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.65.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.65.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.66.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.66.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.66.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.67.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.67.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.67.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.68.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.68.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.68.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.69.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.69.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.69.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.7.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.7.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.7.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.70.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.70.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.70.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.71.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.71.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.71.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.72.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.72.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.72.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.73.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.73.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.73.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.74.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.74.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.74.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.75.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.75.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.75.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.76.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.76.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.76.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.77.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.77.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.77.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.78.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.78.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.78.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.79.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.79.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.79.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.8.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.8.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.8.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.80.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.80.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.80.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.81.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.81.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.81.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.82.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.82.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.82.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.83.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.83.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.83.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.84.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.84.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.84.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.85.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.85.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.85.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.86.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.86.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.86.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.87.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.87.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.87.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.88.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.88.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.88.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.89.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.89.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.89.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.9.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.9.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.9.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.90.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.90.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.90.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.91.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.91.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.91.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.92.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.92.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.92.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.93.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.93.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.93.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.94.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.94.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.94.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.95.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.95.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.95.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.96.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.96.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.96.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.97.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.97.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.97.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.98.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.98.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.98.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.99.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.99.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.experts.99.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.gate.e_score_correction_bias": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.gate.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.shared_experts.down_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.shared_experts.gate_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.mlp.shared_experts.up_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00008-of-00092.safetensors", + "model.layers.7.self_attn.k_norm.weight": "model-00008-of-00092.safetensors", + "model.layers.7.self_attn.k_proj.bias": "model-00008-of-00092.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.self_attn.q_norm.weight": "model-00008-of-00092.safetensors", + "model.layers.7.self_attn.q_proj.bias": "model-00008-of-00092.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.7.self_attn.v_proj.bias": "model-00008-of-00092.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00008-of-00092.safetensors", + "model.layers.8.input_layernorm.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.0.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.0.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.0.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.1.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.1.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.1.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.10.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.10.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.10.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.100.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.100.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.100.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.101.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.101.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.101.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.102.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.102.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.102.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.103.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.103.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.103.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.104.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.104.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.104.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.105.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.105.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.105.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.106.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.106.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.106.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.107.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.107.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.107.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.108.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.108.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.108.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.109.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.109.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.109.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.11.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.11.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.11.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.110.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.110.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.110.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.111.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.111.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.111.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.112.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.112.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.112.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.113.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.113.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.113.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.114.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.114.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.114.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.115.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.115.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.115.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.116.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.116.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.116.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.117.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.117.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.117.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.118.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.118.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.118.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.119.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.119.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.119.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.12.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.12.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.12.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.120.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.120.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.120.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.121.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.121.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.121.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.122.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.122.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.122.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.123.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.123.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.123.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.124.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.124.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.124.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.125.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.125.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.125.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.126.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.126.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.126.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.127.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.127.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.127.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.128.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.128.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.128.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.129.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.129.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.129.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.13.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.13.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.13.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.130.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.130.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.130.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.131.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.131.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.131.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.132.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.132.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.132.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.133.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.133.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.133.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.134.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.134.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.134.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.135.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.135.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.135.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.136.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.136.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.136.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.137.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.137.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.137.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.138.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.138.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.138.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.139.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.139.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.139.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.14.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.14.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.14.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.140.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.140.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.140.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.141.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.141.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.141.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.142.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.142.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.142.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.143.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.143.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.143.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.144.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.144.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.144.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.145.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.145.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.145.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.146.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.146.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.146.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.147.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.147.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.147.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.148.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.148.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.148.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.149.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.149.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.149.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.15.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.15.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.15.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.150.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.150.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.150.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.151.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.151.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.151.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.152.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.152.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.152.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.153.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.153.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.153.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.154.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.154.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.154.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.155.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.155.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.155.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.156.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.156.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.156.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.157.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.157.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.157.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.158.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.158.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.158.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.159.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.159.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.159.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.16.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.16.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.16.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.17.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.17.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.17.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.18.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.18.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.18.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.19.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.19.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.19.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.2.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.2.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.2.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.20.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.20.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.20.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.21.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.21.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.21.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.22.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.22.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.22.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.23.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.23.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.23.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.24.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.24.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.24.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.25.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.25.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.25.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.26.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.26.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.26.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.27.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.27.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.27.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.28.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.28.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.28.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.29.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.29.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.29.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.3.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.3.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.3.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.30.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.30.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.30.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.31.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.31.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.31.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.32.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.32.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.32.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.33.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.33.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.33.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.34.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.34.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.34.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.35.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.35.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.35.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.36.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.36.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.36.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.37.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.37.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.37.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.38.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.38.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.38.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.39.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.39.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.39.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.4.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.4.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.4.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.40.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.40.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.40.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.41.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.41.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.41.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.42.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.42.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.42.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.43.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.43.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.43.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.44.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.44.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.44.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.45.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.45.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.45.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.46.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.46.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.46.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.47.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.47.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.47.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.48.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.48.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.48.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.49.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.49.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.49.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.5.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.5.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.5.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.50.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.50.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.50.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.51.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.51.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.51.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.52.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.52.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.52.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.53.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.53.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.53.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.54.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.54.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.54.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.55.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.55.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.55.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.56.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.56.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.56.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.57.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.57.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.57.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.58.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.58.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.58.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.59.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.59.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.59.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.6.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.6.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.6.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.60.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.60.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.60.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.61.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.61.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.61.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.62.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.62.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.62.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.63.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.63.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.63.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.64.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.64.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.64.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.65.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.65.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.65.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.66.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.66.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.66.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.67.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.67.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.67.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.68.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.68.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.68.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.69.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.69.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.69.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.7.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.7.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.7.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.70.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.70.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.70.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.71.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.71.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.71.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.72.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.72.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.72.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.73.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.73.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.73.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.74.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.74.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.74.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.75.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.75.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.75.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.76.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.76.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.76.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.77.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.77.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.77.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.78.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.78.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.78.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.79.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.79.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.79.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.8.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.8.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.8.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.80.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.80.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.80.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.81.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.81.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.81.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.82.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.82.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.82.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.83.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.83.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.83.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.84.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.84.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.84.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.85.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.85.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.85.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.86.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.86.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.86.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.87.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.87.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.87.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.88.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.88.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.88.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.89.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.89.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.89.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.9.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.9.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.9.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.90.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.90.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.90.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.91.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.91.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.91.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.92.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.92.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.92.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.93.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.93.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.93.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.94.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.94.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.94.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.95.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.95.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.95.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.96.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.96.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.96.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.97.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.97.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.97.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.98.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.98.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.98.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.99.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.99.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.experts.99.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.gate.e_score_correction_bias": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.gate.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.shared_experts.down_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.shared_experts.gate_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.mlp.shared_experts.up_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00009-of-00092.safetensors", + "model.layers.8.self_attn.k_norm.weight": "model-00009-of-00092.safetensors", + "model.layers.8.self_attn.k_proj.bias": "model-00009-of-00092.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.self_attn.q_norm.weight": "model-00009-of-00092.safetensors", + "model.layers.8.self_attn.q_proj.bias": "model-00009-of-00092.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.8.self_attn.v_proj.bias": "model-00009-of-00092.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00009-of-00092.safetensors", + "model.layers.9.input_layernorm.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.0.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.0.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.0.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.1.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.1.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.1.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.10.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.10.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.10.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.100.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.100.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.100.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.101.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.101.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.101.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.102.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.102.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.102.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.103.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.103.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.103.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.104.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.104.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.104.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.105.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.105.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.105.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.106.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.106.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.106.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.107.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.107.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.107.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.108.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.108.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.108.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.109.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.109.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.109.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.11.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.11.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.11.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.110.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.110.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.110.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.111.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.111.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.111.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.112.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.112.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.112.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.113.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.113.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.113.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.114.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.114.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.114.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.115.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.115.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.115.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.116.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.116.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.116.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.117.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.117.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.117.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.118.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.118.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.118.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.119.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.119.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.119.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.12.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.12.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.12.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.120.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.120.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.120.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.121.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.121.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.121.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.122.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.122.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.122.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.123.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.123.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.123.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.124.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.124.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.124.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.125.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.125.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.125.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.126.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.126.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.126.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.127.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.127.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.127.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.128.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.128.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.128.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.129.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.129.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.129.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.13.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.13.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.13.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.130.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.130.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.130.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.131.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.131.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.131.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.132.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.132.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.132.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.133.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.133.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.133.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.134.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.134.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.134.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.135.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.135.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.135.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.136.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.136.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.136.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.137.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.137.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.137.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.138.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.138.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.138.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.139.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.139.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.139.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.14.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.14.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.14.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.140.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.140.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.140.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.141.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.141.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.141.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.142.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.142.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.142.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.143.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.143.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.143.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.144.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.144.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.144.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.145.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.145.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.145.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.146.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.146.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.146.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.147.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.147.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.147.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.148.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.148.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.148.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.149.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.149.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.149.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.15.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.15.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.15.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.150.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.150.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.150.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.151.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.151.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.151.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.152.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.152.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.152.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.153.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.153.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.153.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.154.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.154.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.154.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.155.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.155.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.155.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.156.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.156.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.156.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.157.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.157.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.157.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.158.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.158.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.158.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.159.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.159.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.159.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.16.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.16.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.16.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.17.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.17.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.17.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.18.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.18.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.18.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.19.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.19.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.19.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.2.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.2.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.2.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.20.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.20.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.20.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.21.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.21.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.21.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.22.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.22.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.22.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.23.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.23.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.23.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.24.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.24.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.24.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.25.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.25.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.25.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.26.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.26.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.26.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.27.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.27.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.27.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.28.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.28.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.28.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.29.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.29.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.29.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.3.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.3.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.3.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.30.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.30.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.30.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.31.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.31.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.31.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.32.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.32.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.32.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.33.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.33.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.33.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.34.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.34.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.34.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.35.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.35.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.35.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.36.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.36.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.36.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.37.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.37.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.37.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.38.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.38.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.38.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.39.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.39.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.39.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.4.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.4.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.4.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.40.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.40.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.40.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.41.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.41.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.41.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.42.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.42.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.42.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.43.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.43.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.43.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.44.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.44.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.44.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.45.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.45.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.45.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.46.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.46.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.46.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.47.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.47.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.47.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.48.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.48.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.48.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.49.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.49.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.49.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.5.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.5.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.5.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.50.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.50.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.50.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.51.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.51.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.51.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.52.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.52.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.52.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.53.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.53.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.53.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.54.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.54.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.54.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.55.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.55.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.55.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.56.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.56.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.56.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.57.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.57.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.57.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.58.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.58.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.58.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.59.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.59.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.59.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.6.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.6.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.6.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.60.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.60.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.60.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.61.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.61.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.61.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.62.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.62.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.62.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.63.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.63.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.63.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.64.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.64.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.64.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.65.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.65.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.65.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.66.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.66.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.66.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.67.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.67.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.67.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.68.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.68.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.68.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.69.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.69.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.69.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.7.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.7.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.7.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.70.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.70.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.70.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.71.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.71.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.71.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.72.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.72.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.72.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.73.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.73.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.73.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.74.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.74.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.74.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.75.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.75.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.75.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.76.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.76.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.76.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.77.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.77.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.77.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.78.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.78.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.78.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.79.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.79.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.79.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.8.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.8.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.8.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.80.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.80.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.80.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.81.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.81.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.81.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.82.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.82.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.82.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.83.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.83.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.83.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.84.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.84.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.84.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.85.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.85.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.85.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.86.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.86.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.86.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.87.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.87.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.87.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.88.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.88.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.88.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.89.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.89.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.89.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.9.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.9.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.9.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.90.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.90.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.90.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.91.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.91.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.91.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.92.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.92.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.92.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.93.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.93.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.93.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.94.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.94.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.94.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.95.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.95.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.95.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.96.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.96.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.96.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.97.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.97.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.97.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.98.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.98.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.98.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.99.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.99.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.experts.99.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.gate.e_score_correction_bias": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.gate.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.shared_experts.down_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.shared_experts.gate_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.mlp.shared_experts.up_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00010-of-00092.safetensors", + "model.layers.9.self_attn.k_norm.weight": "model-00010-of-00092.safetensors", + "model.layers.9.self_attn.k_proj.bias": "model-00010-of-00092.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.self_attn.q_norm.weight": "model-00010-of-00092.safetensors", + "model.layers.9.self_attn.q_proj.bias": "model-00010-of-00092.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.9.self_attn.v_proj.bias": "model-00010-of-00092.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00010-of-00092.safetensors", + "model.layers.10.input_layernorm.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.0.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.0.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.0.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.1.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.1.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.1.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.10.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.10.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.10.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.100.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.100.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.100.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.101.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.101.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.101.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.102.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.102.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.102.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.103.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.103.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.103.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.104.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.104.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.104.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.105.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.105.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.105.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.106.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.106.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.106.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.107.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.107.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.107.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.108.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.108.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.108.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.109.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.109.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.109.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.11.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.11.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.11.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.110.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.110.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.110.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.111.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.111.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.111.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.112.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.112.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.112.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.113.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.113.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.113.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.114.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.114.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.114.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.115.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.115.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.115.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.116.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.116.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.116.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.117.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.117.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.117.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.118.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.118.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.118.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.119.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.119.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.119.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.12.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.12.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.12.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.120.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.120.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.120.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.121.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.121.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.121.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.122.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.122.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.122.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.123.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.123.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.123.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.124.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.124.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.124.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.125.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.125.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.125.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.126.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.126.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.126.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.127.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.127.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.127.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.128.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.128.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.128.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.129.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.129.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.129.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.13.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.13.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.13.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.130.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.130.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.130.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.131.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.131.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.131.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.132.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.132.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.132.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.133.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.133.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.133.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.134.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.134.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.134.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.135.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.135.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.135.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.136.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.136.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.136.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.137.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.137.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.137.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.138.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.138.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.138.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.139.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.139.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.139.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.14.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.14.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.14.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.140.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.140.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.140.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.141.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.141.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.141.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.142.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.142.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.142.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.143.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.143.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.143.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.144.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.144.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.144.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.145.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.145.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.145.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.146.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.146.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.146.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.147.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.147.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.147.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.148.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.148.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.148.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.149.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.149.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.149.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.15.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.15.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.15.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.150.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.150.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.150.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.151.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.151.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.151.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.152.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.152.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.152.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.153.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.153.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.153.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.154.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.154.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.154.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.155.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.155.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.155.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.156.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.156.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.156.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.157.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.157.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.157.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.158.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.158.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.158.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.159.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.159.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.159.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.16.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.16.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.16.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.17.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.17.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.17.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.18.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.18.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.18.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.19.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.19.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.19.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.2.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.2.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.2.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.20.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.20.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.20.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.21.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.21.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.21.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.22.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.22.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.22.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.23.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.23.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.23.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.24.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.24.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.24.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.25.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.25.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.25.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.26.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.26.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.26.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.27.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.27.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.27.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.28.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.28.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.28.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.29.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.29.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.29.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.3.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.3.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.3.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.30.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.30.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.30.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.31.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.31.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.31.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.32.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.32.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.32.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.33.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.33.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.33.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.34.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.34.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.34.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.35.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.35.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.35.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.36.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.36.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.36.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.37.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.37.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.37.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.38.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.38.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.38.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.39.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.39.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.39.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.4.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.4.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.4.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.40.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.40.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.40.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.41.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.41.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.41.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.42.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.42.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.42.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.43.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.43.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.43.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.44.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.44.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.44.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.45.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.45.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.45.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.46.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.46.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.46.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.47.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.47.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.47.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.48.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.48.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.48.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.49.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.49.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.49.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.5.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.5.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.5.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.50.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.50.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.50.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.51.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.51.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.51.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.52.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.52.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.52.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.53.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.53.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.53.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.54.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.54.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.54.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.55.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.55.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.55.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.56.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.56.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.56.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.57.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.57.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.57.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.58.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.58.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.58.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.59.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.59.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.59.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.6.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.6.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.6.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.60.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.60.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.60.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.61.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.61.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.61.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.62.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.62.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.62.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.63.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.63.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.63.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.64.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.64.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.64.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.65.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.65.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.65.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.66.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.66.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.66.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.67.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.67.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.67.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.68.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.68.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.68.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.69.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.69.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.69.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.7.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.7.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.7.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.70.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.70.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.70.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.71.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.71.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.71.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.72.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.72.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.72.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.73.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.73.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.73.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.74.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.74.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.74.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.75.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.75.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.75.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.76.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.76.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.76.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.77.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.77.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.77.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.78.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.78.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.78.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.79.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.79.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.79.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.8.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.8.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.8.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.80.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.80.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.80.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.81.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.81.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.81.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.82.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.82.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.82.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.83.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.83.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.83.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.84.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.84.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.84.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.85.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.85.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.85.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.86.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.86.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.86.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.87.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.87.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.87.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.88.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.88.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.88.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.89.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.89.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.89.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.9.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.9.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.9.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.90.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.90.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.90.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.91.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.91.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.91.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.92.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.92.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.92.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.93.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.93.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.93.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.94.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.94.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.94.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.95.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.95.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.95.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.96.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.96.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.96.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.97.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.97.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.97.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.98.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.98.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.98.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.99.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.99.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.experts.99.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.gate.e_score_correction_bias": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.gate.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.shared_experts.down_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.shared_experts.gate_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.mlp.shared_experts.up_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00011-of-00092.safetensors", + "model.layers.10.self_attn.k_norm.weight": "model-00011-of-00092.safetensors", + "model.layers.10.self_attn.k_proj.bias": "model-00011-of-00092.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.self_attn.q_norm.weight": "model-00011-of-00092.safetensors", + "model.layers.10.self_attn.q_proj.bias": "model-00011-of-00092.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.10.self_attn.v_proj.bias": "model-00011-of-00092.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00011-of-00092.safetensors", + "model.layers.11.input_layernorm.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.0.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.0.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.0.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.1.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.1.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.1.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.10.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.10.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.10.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.100.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.100.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.100.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.101.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.101.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.101.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.102.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.102.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.102.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.103.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.103.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.103.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.104.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.104.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.104.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.105.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.105.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.105.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.106.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.106.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.106.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.107.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.107.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.107.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.108.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.108.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.108.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.109.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.109.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.109.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.11.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.11.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.11.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.110.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.110.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.110.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.111.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.111.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.111.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.112.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.112.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.112.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.113.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.113.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.113.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.114.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.114.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.114.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.115.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.115.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.115.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.116.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.116.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.116.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.117.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.117.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.117.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.118.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.118.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.118.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.119.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.119.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.119.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.12.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.12.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.12.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.120.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.120.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.120.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.121.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.121.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.121.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.122.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.122.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.122.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.123.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.123.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.123.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.124.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.124.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.124.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.125.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.125.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.125.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.126.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.126.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.126.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.127.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.127.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.127.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.128.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.128.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.128.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.129.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.129.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.129.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.13.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.13.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.13.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.130.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.130.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.130.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.131.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.131.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.131.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.132.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.132.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.132.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.133.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.133.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.133.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.134.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.134.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.134.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.135.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.135.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.135.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.136.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.136.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.136.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.137.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.137.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.137.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.138.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.138.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.138.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.139.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.139.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.139.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.14.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.14.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.14.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.140.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.140.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.140.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.141.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.141.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.141.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.142.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.142.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.142.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.143.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.143.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.143.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.144.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.144.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.144.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.145.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.145.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.145.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.146.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.146.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.146.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.147.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.147.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.147.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.148.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.148.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.148.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.149.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.149.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.149.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.15.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.15.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.15.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.150.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.150.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.150.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.151.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.151.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.151.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.152.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.152.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.152.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.153.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.153.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.153.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.154.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.154.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.154.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.155.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.155.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.155.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.156.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.156.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.156.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.157.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.157.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.157.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.158.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.158.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.158.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.159.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.159.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.159.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.16.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.16.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.16.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.17.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.17.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.17.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.18.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.18.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.18.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.19.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.19.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.19.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.2.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.2.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.2.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.20.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.20.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.20.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.21.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.21.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.21.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.22.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.22.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.22.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.23.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.23.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.23.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.24.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.24.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.24.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.25.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.25.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.25.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.26.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.26.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.26.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.27.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.27.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.27.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.28.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.28.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.28.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.29.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.29.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.29.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.3.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.3.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.3.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.30.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.30.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.30.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.31.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.31.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.31.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.32.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.32.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.32.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.33.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.33.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.33.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.34.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.34.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.34.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.35.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.35.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.35.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.36.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.36.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.36.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.37.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.37.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.37.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.38.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.38.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.38.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.39.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.39.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.39.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.4.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.4.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.4.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.40.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.40.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.40.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.41.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.41.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.41.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.42.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.42.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.42.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.43.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.43.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.43.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.44.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.44.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.44.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.45.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.45.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.45.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.46.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.46.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.46.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.47.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.47.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.47.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.48.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.48.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.48.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.49.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.49.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.49.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.5.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.5.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.5.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.50.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.50.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.50.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.51.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.51.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.51.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.52.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.52.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.52.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.53.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.53.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.53.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.54.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.54.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.54.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.55.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.55.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.55.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.56.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.56.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.56.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.57.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.57.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.57.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.58.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.58.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.58.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.59.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.59.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.59.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.6.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.6.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.6.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.60.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.60.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.60.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.61.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.61.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.61.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.62.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.62.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.62.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.63.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.63.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.63.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.64.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.64.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.64.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.65.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.65.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.65.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.66.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.66.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.66.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.67.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.67.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.67.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.68.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.68.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.68.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.69.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.69.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.69.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.7.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.7.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.7.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.70.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.70.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.70.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.71.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.71.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.71.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.72.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.72.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.72.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.73.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.73.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.73.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.74.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.74.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.74.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.75.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.75.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.75.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.76.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.76.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.76.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.77.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.77.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.77.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.78.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.78.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.78.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.79.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.79.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.79.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.8.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.8.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.8.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.80.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.80.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.80.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.81.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.81.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.81.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.82.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.82.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.82.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.83.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.83.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.83.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.84.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.84.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.84.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.85.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.85.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.85.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.86.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.86.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.86.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.87.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.87.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.87.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.88.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.88.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.88.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.89.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.89.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.89.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.9.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.9.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.9.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.90.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.90.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.90.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.91.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.91.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.91.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.92.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.92.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.92.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.93.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.93.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.93.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.94.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.94.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.94.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.95.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.95.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.95.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.96.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.96.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.96.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.97.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.97.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.97.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.98.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.98.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.98.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.99.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.99.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.experts.99.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.gate.e_score_correction_bias": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.gate.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.shared_experts.down_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.shared_experts.gate_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.mlp.shared_experts.up_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00012-of-00092.safetensors", + "model.layers.11.self_attn.k_norm.weight": "model-00012-of-00092.safetensors", + "model.layers.11.self_attn.k_proj.bias": "model-00012-of-00092.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.self_attn.q_norm.weight": "model-00012-of-00092.safetensors", + "model.layers.11.self_attn.q_proj.bias": "model-00012-of-00092.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.11.self_attn.v_proj.bias": "model-00012-of-00092.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00012-of-00092.safetensors", + "model.layers.12.input_layernorm.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.0.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.0.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.0.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.1.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.1.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.1.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.10.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.10.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.10.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.100.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.100.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.100.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.101.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.101.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.101.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.102.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.102.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.102.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.103.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.103.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.103.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.104.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.104.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.104.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.105.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.105.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.105.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.106.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.106.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.106.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.107.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.107.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.107.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.108.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.108.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.108.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.109.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.109.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.109.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.11.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.11.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.11.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.110.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.110.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.110.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.111.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.111.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.111.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.112.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.112.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.112.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.113.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.113.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.113.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.114.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.114.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.114.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.115.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.115.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.115.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.116.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.116.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.116.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.117.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.117.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.117.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.118.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.118.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.118.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.119.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.119.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.119.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.12.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.12.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.12.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.120.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.120.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.120.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.121.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.121.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.121.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.122.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.122.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.122.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.123.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.123.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.123.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.124.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.124.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.124.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.125.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.125.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.125.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.126.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.126.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.126.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.127.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.127.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.127.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.128.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.128.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.128.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.129.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.129.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.129.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.13.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.13.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.13.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.130.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.130.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.130.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.131.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.131.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.131.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.132.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.132.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.132.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.133.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.133.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.133.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.134.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.134.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.134.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.135.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.135.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.135.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.136.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.136.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.136.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.137.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.137.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.137.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.138.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.138.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.138.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.139.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.139.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.139.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.14.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.14.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.14.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.140.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.140.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.140.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.141.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.141.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.141.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.142.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.142.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.142.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.143.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.143.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.143.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.144.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.144.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.144.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.145.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.145.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.145.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.146.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.146.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.146.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.147.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.147.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.147.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.148.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.148.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.148.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.149.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.149.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.149.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.15.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.15.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.15.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.150.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.150.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.150.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.151.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.151.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.151.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.152.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.152.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.152.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.153.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.153.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.153.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.154.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.154.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.154.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.155.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.155.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.155.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.156.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.156.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.156.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.157.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.157.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.157.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.158.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.158.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.158.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.159.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.159.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.159.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.16.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.16.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.16.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.17.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.17.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.17.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.18.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.18.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.18.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.19.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.19.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.19.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.2.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.2.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.2.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.20.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.20.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.20.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.21.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.21.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.21.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.22.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.22.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.22.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.23.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.23.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.23.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.24.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.24.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.24.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.25.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.25.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.25.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.26.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.26.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.26.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.27.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.27.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.27.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.28.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.28.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.28.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.29.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.29.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.29.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.3.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.3.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.3.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.30.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.30.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.30.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.31.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.31.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.31.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.32.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.32.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.32.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.33.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.33.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.33.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.34.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.34.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.34.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.35.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.35.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.35.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.36.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.36.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.36.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.37.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.37.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.37.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.38.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.38.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.38.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.39.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.39.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.39.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.4.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.4.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.4.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.40.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.40.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.40.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.41.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.41.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.41.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.42.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.42.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.42.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.43.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.43.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.43.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.44.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.44.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.44.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.45.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.45.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.45.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.46.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.46.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.46.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.47.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.47.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.47.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.48.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.48.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.48.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.49.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.49.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.49.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.5.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.5.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.5.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.50.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.50.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.50.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.51.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.51.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.51.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.52.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.52.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.52.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.53.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.53.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.53.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.54.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.54.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.54.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.55.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.55.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.55.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.56.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.56.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.56.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.57.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.57.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.57.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.58.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.58.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.58.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.59.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.59.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.59.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.6.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.6.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.6.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.60.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.60.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.60.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.61.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.61.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.61.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.62.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.62.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.62.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.63.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.63.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.63.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.64.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.64.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.64.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.65.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.65.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.65.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.66.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.66.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.66.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.67.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.67.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.67.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.68.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.68.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.68.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.69.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.69.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.69.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.7.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.7.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.7.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.70.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.70.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.70.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.71.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.71.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.71.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.72.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.72.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.72.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.73.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.73.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.73.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.74.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.74.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.74.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.75.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.75.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.75.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.76.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.76.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.76.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.77.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.77.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.77.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.78.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.78.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.78.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.79.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.79.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.79.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.8.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.8.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.8.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.80.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.80.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.80.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.81.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.81.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.81.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.82.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.82.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.82.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.83.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.83.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.83.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.84.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.84.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.84.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.85.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.85.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.85.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.86.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.86.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.86.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.87.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.87.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.87.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.88.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.88.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.88.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.89.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.89.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.89.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.9.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.9.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.9.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.90.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.90.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.90.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.91.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.91.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.91.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.92.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.92.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.92.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.93.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.93.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.93.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.94.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.94.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.94.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.95.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.95.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.95.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.96.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.96.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.96.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.97.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.97.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.97.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.98.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.98.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.98.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.99.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.99.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.experts.99.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.gate.e_score_correction_bias": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.gate.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.shared_experts.down_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.shared_experts.gate_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.mlp.shared_experts.up_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00013-of-00092.safetensors", + "model.layers.12.self_attn.k_norm.weight": "model-00013-of-00092.safetensors", + "model.layers.12.self_attn.k_proj.bias": "model-00013-of-00092.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.self_attn.q_norm.weight": "model-00013-of-00092.safetensors", + "model.layers.12.self_attn.q_proj.bias": "model-00013-of-00092.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.12.self_attn.v_proj.bias": "model-00013-of-00092.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00013-of-00092.safetensors", + "model.layers.13.input_layernorm.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.0.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.0.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.0.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.1.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.1.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.1.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.10.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.10.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.10.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.100.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.100.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.100.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.101.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.101.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.101.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.102.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.102.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.102.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.103.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.103.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.103.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.104.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.104.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.104.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.105.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.105.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.105.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.106.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.106.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.106.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.107.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.107.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.107.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.108.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.108.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.108.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.109.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.109.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.109.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.11.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.11.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.11.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.110.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.110.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.110.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.111.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.111.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.111.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.112.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.112.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.112.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.113.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.113.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.113.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.114.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.114.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.114.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.115.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.115.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.115.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.116.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.116.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.116.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.117.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.117.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.117.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.118.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.118.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.118.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.119.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.119.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.119.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.12.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.12.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.12.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.120.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.120.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.120.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.121.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.121.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.121.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.122.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.122.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.122.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.123.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.123.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.123.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.124.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.124.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.124.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.125.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.125.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.125.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.126.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.126.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.126.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.127.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.127.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.127.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.128.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.128.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.128.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.129.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.129.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.129.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.13.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.13.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.13.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.130.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.130.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.130.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.131.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.131.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.131.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.132.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.132.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.132.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.133.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.133.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.133.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.134.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.134.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.134.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.135.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.135.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.135.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.136.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.136.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.136.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.137.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.137.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.137.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.138.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.138.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.138.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.139.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.139.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.139.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.14.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.14.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.14.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.140.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.140.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.140.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.141.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.141.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.141.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.142.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.142.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.142.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.143.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.143.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.143.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.144.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.144.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.144.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.145.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.145.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.145.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.146.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.146.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.146.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.147.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.147.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.147.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.148.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.148.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.148.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.149.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.149.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.149.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.15.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.15.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.15.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.150.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.150.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.150.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.151.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.151.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.151.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.152.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.152.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.152.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.153.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.153.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.153.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.154.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.154.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.154.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.155.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.155.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.155.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.156.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.156.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.156.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.157.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.157.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.157.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.158.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.158.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.158.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.159.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.159.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.159.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.16.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.16.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.16.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.17.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.17.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.17.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.18.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.18.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.18.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.19.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.19.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.19.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.2.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.2.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.2.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.20.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.20.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.20.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.21.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.21.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.21.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.22.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.22.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.22.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.23.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.23.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.23.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.24.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.24.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.24.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.25.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.25.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.25.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.26.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.26.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.26.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.27.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.27.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.27.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.28.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.28.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.28.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.29.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.29.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.29.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.3.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.3.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.3.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.30.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.30.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.30.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.31.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.31.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.31.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.32.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.32.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.32.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.33.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.33.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.33.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.34.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.34.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.34.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.35.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.35.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.35.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.36.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.36.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.36.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.37.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.37.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.37.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.38.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.38.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.38.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.39.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.39.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.39.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.4.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.4.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.4.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.40.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.40.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.40.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.41.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.41.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.41.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.42.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.42.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.42.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.43.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.43.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.43.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.44.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.44.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.44.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.45.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.45.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.45.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.46.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.46.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.46.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.47.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.47.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.47.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.48.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.48.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.48.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.49.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.49.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.49.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.5.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.5.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.5.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.50.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.50.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.50.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.51.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.51.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.51.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.52.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.52.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.52.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.53.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.53.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.53.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.54.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.54.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.54.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.55.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.55.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.55.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.56.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.56.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.56.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.57.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.57.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.57.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.58.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.58.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.58.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.59.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.59.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.59.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.6.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.6.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.6.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.60.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.60.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.60.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.61.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.61.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.61.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.62.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.62.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.62.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.63.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.63.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.63.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.64.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.64.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.64.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.65.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.65.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.65.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.66.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.66.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.66.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.67.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.67.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.67.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.68.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.68.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.68.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.69.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.69.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.69.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.7.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.7.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.7.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.70.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.70.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.70.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.71.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.71.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.71.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.72.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.72.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.72.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.73.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.73.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.73.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.74.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.74.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.74.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.75.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.75.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.75.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.76.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.76.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.76.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.77.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.77.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.77.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.78.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.78.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.78.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.79.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.79.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.79.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.8.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.8.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.8.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.80.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.80.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.80.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.81.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.81.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.81.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.82.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.82.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.82.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.83.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.83.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.83.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.84.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.84.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.84.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.85.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.85.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.85.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.86.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.86.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.86.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.87.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.87.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.87.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.88.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.88.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.88.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.89.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.89.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.89.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.9.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.9.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.9.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.90.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.90.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.90.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.91.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.91.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.91.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.92.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.92.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.92.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.93.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.93.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.93.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.94.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.94.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.94.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.95.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.95.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.95.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.96.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.96.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.96.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.97.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.97.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.97.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.98.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.98.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.98.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.99.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.99.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.experts.99.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.gate.e_score_correction_bias": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.gate.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.shared_experts.down_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.shared_experts.gate_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.mlp.shared_experts.up_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00014-of-00092.safetensors", + "model.layers.13.self_attn.k_norm.weight": "model-00014-of-00092.safetensors", + "model.layers.13.self_attn.k_proj.bias": "model-00014-of-00092.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.self_attn.q_norm.weight": "model-00014-of-00092.safetensors", + "model.layers.13.self_attn.q_proj.bias": "model-00014-of-00092.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.13.self_attn.v_proj.bias": "model-00014-of-00092.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00014-of-00092.safetensors", + "model.layers.14.input_layernorm.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.0.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.0.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.0.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.1.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.1.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.1.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.10.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.10.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.10.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.100.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.100.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.100.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.101.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.101.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.101.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.102.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.102.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.102.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.103.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.103.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.103.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.104.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.104.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.104.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.105.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.105.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.105.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.106.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.106.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.106.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.107.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.107.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.107.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.108.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.108.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.108.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.109.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.109.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.109.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.11.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.11.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.11.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.110.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.110.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.110.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.111.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.111.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.111.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.112.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.112.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.112.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.113.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.113.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.113.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.114.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.114.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.114.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.115.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.115.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.115.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.116.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.116.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.116.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.117.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.117.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.117.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.118.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.118.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.118.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.119.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.119.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.119.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.12.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.12.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.12.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.120.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.120.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.120.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.121.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.121.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.121.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.122.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.122.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.122.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.123.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.123.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.123.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.124.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.124.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.124.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.125.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.125.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.125.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.126.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.126.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.126.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.127.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.127.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.127.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.128.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.128.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.128.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.129.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.129.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.129.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.13.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.13.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.13.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.130.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.130.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.130.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.131.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.131.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.131.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.132.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.132.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.132.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.133.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.133.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.133.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.134.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.134.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.134.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.135.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.135.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.135.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.136.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.136.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.136.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.137.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.137.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.137.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.138.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.138.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.138.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.139.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.139.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.139.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.14.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.14.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.14.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.140.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.140.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.140.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.141.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.141.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.141.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.142.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.142.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.142.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.143.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.143.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.143.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.144.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.144.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.144.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.145.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.145.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.145.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.146.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.146.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.146.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.147.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.147.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.147.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.148.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.148.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.148.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.149.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.149.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.149.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.15.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.15.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.15.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.150.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.150.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.150.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.151.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.151.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.151.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.152.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.152.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.152.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.153.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.153.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.153.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.154.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.154.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.154.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.155.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.155.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.155.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.156.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.156.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.156.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.157.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.157.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.157.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.158.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.158.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.158.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.159.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.159.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.159.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.16.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.16.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.16.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.17.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.17.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.17.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.18.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.18.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.18.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.19.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.19.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.19.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.2.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.2.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.2.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.20.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.20.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.20.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.21.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.21.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.21.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.22.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.22.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.22.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.23.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.23.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.23.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.24.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.24.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.24.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.25.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.25.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.25.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.26.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.26.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.26.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.27.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.27.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.27.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.28.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.28.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.28.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.29.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.29.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.29.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.3.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.3.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.3.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.30.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.30.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.30.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.31.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.31.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.31.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.32.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.32.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.32.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.33.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.33.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.33.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.34.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.34.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.34.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.35.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.35.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.35.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.36.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.36.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.36.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.37.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.37.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.37.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.38.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.38.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.38.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.39.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.39.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.39.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.4.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.4.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.4.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.40.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.40.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.40.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.41.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.41.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.41.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.42.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.42.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.42.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.43.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.43.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.43.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.44.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.44.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.44.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.45.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.45.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.45.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.46.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.46.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.46.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.47.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.47.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.47.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.48.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.48.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.48.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.49.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.49.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.49.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.5.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.5.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.5.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.50.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.50.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.50.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.51.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.51.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.51.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.52.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.52.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.52.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.53.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.53.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.53.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.54.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.54.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.54.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.55.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.55.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.55.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.56.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.56.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.56.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.57.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.57.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.57.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.58.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.58.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.58.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.59.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.59.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.59.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.6.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.6.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.6.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.60.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.60.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.60.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.61.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.61.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.61.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.62.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.62.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.62.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.63.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.63.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.63.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.64.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.64.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.64.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.65.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.65.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.65.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.66.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.66.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.66.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.67.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.67.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.67.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.68.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.68.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.68.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.69.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.69.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.69.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.7.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.7.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.7.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.70.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.70.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.70.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.71.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.71.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.71.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.72.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.72.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.72.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.73.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.73.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.73.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.74.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.74.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.74.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.75.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.75.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.75.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.76.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.76.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.76.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.77.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.77.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.77.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.78.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.78.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.78.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.79.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.79.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.79.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.8.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.8.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.8.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.80.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.80.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.80.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.81.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.81.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.81.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.82.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.82.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.82.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.83.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.83.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.83.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.84.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.84.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.84.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.85.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.85.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.85.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.86.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.86.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.86.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.87.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.87.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.87.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.88.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.88.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.88.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.89.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.89.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.89.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.9.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.9.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.9.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.90.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.90.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.90.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.91.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.91.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.91.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.92.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.92.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.92.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.93.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.93.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.93.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.94.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.94.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.94.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.95.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.95.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.95.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.96.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.96.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.96.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.97.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.97.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.97.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.98.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.98.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.98.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.99.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.99.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.experts.99.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.gate.e_score_correction_bias": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.gate.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.shared_experts.down_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.shared_experts.gate_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.mlp.shared_experts.up_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00015-of-00092.safetensors", + "model.layers.14.self_attn.k_norm.weight": "model-00015-of-00092.safetensors", + "model.layers.14.self_attn.k_proj.bias": "model-00015-of-00092.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.self_attn.q_norm.weight": "model-00015-of-00092.safetensors", + "model.layers.14.self_attn.q_proj.bias": "model-00015-of-00092.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.14.self_attn.v_proj.bias": "model-00015-of-00092.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00015-of-00092.safetensors", + "model.layers.15.input_layernorm.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.0.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.0.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.0.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.1.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.1.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.1.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.10.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.10.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.10.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.100.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.100.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.100.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.101.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.101.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.101.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.102.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.102.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.102.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.103.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.103.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.103.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.104.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.104.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.104.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.105.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.105.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.105.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.106.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.106.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.106.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.107.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.107.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.107.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.108.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.108.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.108.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.109.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.109.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.109.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.11.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.11.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.11.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.110.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.110.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.110.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.111.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.111.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.111.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.112.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.112.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.112.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.113.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.113.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.113.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.114.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.114.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.114.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.115.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.115.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.115.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.116.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.116.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.116.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.117.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.117.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.117.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.118.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.118.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.118.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.119.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.119.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.119.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.12.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.12.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.12.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.120.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.120.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.120.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.121.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.121.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.121.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.122.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.122.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.122.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.123.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.123.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.123.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.124.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.124.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.124.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.125.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.125.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.125.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.126.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.126.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.126.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.127.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.127.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.127.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.128.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.128.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.128.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.129.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.129.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.129.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.13.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.13.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.13.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.130.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.130.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.130.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.131.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.131.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.131.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.132.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.132.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.132.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.133.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.133.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.133.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.134.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.134.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.134.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.135.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.135.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.135.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.136.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.136.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.136.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.137.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.137.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.137.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.138.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.138.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.138.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.139.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.139.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.139.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.14.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.14.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.14.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.140.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.140.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.140.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.141.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.141.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.141.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.142.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.142.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.142.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.143.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.143.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.143.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.144.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.144.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.144.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.145.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.145.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.145.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.146.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.146.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.146.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.147.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.147.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.147.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.148.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.148.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.148.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.149.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.149.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.149.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.15.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.15.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.15.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.150.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.150.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.150.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.151.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.151.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.151.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.152.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.152.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.152.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.153.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.153.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.153.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.154.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.154.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.154.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.155.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.155.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.155.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.156.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.156.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.156.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.157.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.157.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.157.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.158.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.158.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.158.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.159.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.159.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.159.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.16.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.16.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.16.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.17.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.17.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.17.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.18.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.18.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.18.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.19.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.19.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.19.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.2.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.2.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.2.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.20.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.20.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.20.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.21.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.21.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.21.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.22.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.22.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.22.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.23.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.23.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.23.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.24.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.24.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.24.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.25.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.25.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.25.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.26.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.26.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.26.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.27.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.27.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.27.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.28.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.28.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.28.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.29.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.29.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.29.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.3.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.3.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.3.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.30.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.30.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.30.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.31.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.31.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.31.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.32.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.32.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.32.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.33.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.33.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.33.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.34.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.34.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.34.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.35.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.35.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.35.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.36.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.36.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.36.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.37.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.37.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.37.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.38.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.38.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.38.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.39.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.39.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.39.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.4.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.4.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.4.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.40.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.40.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.40.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.41.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.41.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.41.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.42.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.42.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.42.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.43.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.43.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.43.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.44.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.44.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.44.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.45.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.45.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.45.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.46.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.46.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.46.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.47.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.47.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.47.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.48.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.48.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.48.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.49.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.49.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.49.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.5.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.5.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.5.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.50.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.50.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.50.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.51.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.51.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.51.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.52.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.52.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.52.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.53.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.53.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.53.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.54.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.54.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.54.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.55.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.55.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.55.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.56.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.56.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.56.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.57.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.57.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.57.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.58.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.58.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.58.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.59.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.59.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.59.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.6.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.6.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.6.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.60.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.60.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.60.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.61.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.61.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.61.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.62.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.62.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.62.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.63.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.63.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.63.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.64.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.64.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.64.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.65.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.65.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.65.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.66.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.66.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.66.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.67.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.67.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.67.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.68.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.68.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.68.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.69.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.69.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.69.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.7.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.7.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.7.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.70.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.70.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.70.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.71.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.71.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.71.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.72.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.72.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.72.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.73.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.73.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.73.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.74.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.74.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.74.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.75.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.75.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.75.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.76.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.76.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.76.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.77.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.77.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.77.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.78.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.78.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.78.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.79.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.79.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.79.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.8.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.8.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.8.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.80.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.80.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.80.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.81.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.81.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.81.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.82.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.82.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.82.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.83.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.83.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.83.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.84.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.84.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.84.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.85.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.85.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.85.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.86.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.86.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.86.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.87.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.87.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.87.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.88.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.88.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.88.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.89.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.89.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.89.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.9.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.9.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.9.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.90.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.90.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.90.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.91.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.91.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.91.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.92.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.92.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.92.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.93.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.93.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.93.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.94.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.94.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.94.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.95.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.95.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.95.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.96.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.96.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.96.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.97.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.97.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.97.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.98.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.98.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.98.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.99.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.99.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.experts.99.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.gate.e_score_correction_bias": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.gate.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.shared_experts.down_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.shared_experts.gate_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.mlp.shared_experts.up_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00016-of-00092.safetensors", + "model.layers.15.self_attn.k_norm.weight": "model-00016-of-00092.safetensors", + "model.layers.15.self_attn.k_proj.bias": "model-00016-of-00092.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.self_attn.q_norm.weight": "model-00016-of-00092.safetensors", + "model.layers.15.self_attn.q_proj.bias": "model-00016-of-00092.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.15.self_attn.v_proj.bias": "model-00016-of-00092.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00016-of-00092.safetensors", + "model.layers.16.input_layernorm.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.0.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.0.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.0.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.1.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.1.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.1.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.10.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.10.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.10.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.100.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.100.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.100.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.101.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.101.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.101.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.102.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.102.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.102.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.103.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.103.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.103.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.104.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.104.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.104.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.105.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.105.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.105.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.106.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.106.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.106.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.107.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.107.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.107.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.108.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.108.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.108.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.109.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.109.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.109.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.11.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.11.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.11.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.110.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.110.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.110.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.111.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.111.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.111.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.112.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.112.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.112.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.113.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.113.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.113.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.114.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.114.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.114.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.115.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.115.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.115.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.116.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.116.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.116.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.117.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.117.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.117.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.118.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.118.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.118.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.119.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.119.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.119.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.12.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.12.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.12.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.120.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.120.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.120.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.121.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.121.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.121.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.122.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.122.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.122.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.123.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.123.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.123.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.124.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.124.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.124.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.125.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.125.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.125.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.126.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.126.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.126.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.127.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.127.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.127.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.128.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.128.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.128.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.129.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.129.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.129.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.13.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.13.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.13.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.130.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.130.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.130.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.131.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.131.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.131.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.132.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.132.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.132.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.133.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.133.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.133.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.134.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.134.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.134.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.135.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.135.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.135.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.136.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.136.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.136.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.137.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.137.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.137.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.138.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.138.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.138.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.139.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.139.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.139.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.14.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.14.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.14.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.140.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.140.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.140.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.141.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.141.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.141.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.142.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.142.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.142.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.143.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.143.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.143.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.144.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.144.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.144.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.145.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.145.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.145.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.146.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.146.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.146.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.147.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.147.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.147.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.148.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.148.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.148.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.149.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.149.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.149.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.15.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.15.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.15.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.150.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.150.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.150.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.151.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.151.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.151.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.152.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.152.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.152.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.153.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.153.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.153.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.154.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.154.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.154.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.155.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.155.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.155.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.156.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.156.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.156.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.157.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.157.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.157.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.158.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.158.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.158.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.159.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.159.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.159.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.16.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.16.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.16.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.17.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.17.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.17.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.18.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.18.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.18.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.19.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.19.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.19.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.2.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.2.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.2.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.20.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.20.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.20.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.21.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.21.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.21.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.22.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.22.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.22.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.23.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.23.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.23.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.24.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.24.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.24.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.25.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.25.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.25.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.26.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.26.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.26.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.27.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.27.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.27.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.28.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.28.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.28.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.29.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.29.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.29.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.3.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.3.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.3.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.30.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.30.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.30.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.31.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.31.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.31.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.32.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.32.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.32.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.33.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.33.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.33.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.34.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.34.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.34.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.35.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.35.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.35.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.36.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.36.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.36.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.37.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.37.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.37.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.38.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.38.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.38.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.39.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.39.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.39.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.4.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.4.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.4.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.40.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.40.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.40.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.41.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.41.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.41.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.42.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.42.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.42.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.43.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.43.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.43.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.44.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.44.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.44.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.45.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.45.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.45.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.46.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.46.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.46.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.47.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.47.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.47.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.48.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.48.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.48.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.49.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.49.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.49.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.5.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.5.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.5.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.50.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.50.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.50.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.51.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.51.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.51.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.52.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.52.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.52.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.53.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.53.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.53.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.54.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.54.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.54.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.55.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.55.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.55.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.56.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.56.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.56.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.57.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.57.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.57.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.58.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.58.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.58.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.59.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.59.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.59.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.6.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.6.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.6.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.60.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.60.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.60.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.61.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.61.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.61.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.62.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.62.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.62.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.63.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.63.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.63.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.64.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.64.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.64.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.65.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.65.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.65.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.66.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.66.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.66.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.67.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.67.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.67.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.68.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.68.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.68.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.69.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.69.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.69.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.7.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.7.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.7.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.70.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.70.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.70.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.71.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.71.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.71.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.72.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.72.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.72.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.73.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.73.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.73.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.74.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.74.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.74.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.75.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.75.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.75.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.76.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.76.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.76.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.77.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.77.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.77.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.78.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.78.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.78.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.79.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.79.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.79.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.8.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.8.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.8.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.80.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.80.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.80.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.81.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.81.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.81.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.82.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.82.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.82.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.83.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.83.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.83.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.84.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.84.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.84.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.85.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.85.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.85.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.86.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.86.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.86.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.87.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.87.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.87.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.88.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.88.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.88.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.89.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.89.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.89.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.9.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.9.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.9.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.90.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.90.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.90.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.91.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.91.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.91.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.92.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.92.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.92.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.93.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.93.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.93.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.94.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.94.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.94.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.95.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.95.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.95.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.96.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.96.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.96.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.97.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.97.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.97.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.98.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.98.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.98.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.99.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.99.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.experts.99.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.gate.e_score_correction_bias": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.gate.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.shared_experts.down_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.shared_experts.gate_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.mlp.shared_experts.up_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00017-of-00092.safetensors", + "model.layers.16.self_attn.k_norm.weight": "model-00017-of-00092.safetensors", + "model.layers.16.self_attn.k_proj.bias": "model-00017-of-00092.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.self_attn.q_norm.weight": "model-00017-of-00092.safetensors", + "model.layers.16.self_attn.q_proj.bias": "model-00017-of-00092.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.16.self_attn.v_proj.bias": "model-00017-of-00092.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00017-of-00092.safetensors", + "model.layers.17.input_layernorm.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.0.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.0.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.0.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.1.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.1.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.1.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.10.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.10.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.10.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.100.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.100.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.100.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.101.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.101.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.101.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.102.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.102.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.102.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.103.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.103.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.103.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.104.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.104.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.104.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.105.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.105.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.105.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.106.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.106.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.106.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.107.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.107.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.107.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.108.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.108.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.108.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.109.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.109.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.109.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.11.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.11.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.11.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.110.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.110.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.110.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.111.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.111.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.111.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.112.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.112.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.112.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.113.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.113.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.113.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.114.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.114.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.114.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.115.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.115.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.115.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.116.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.116.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.116.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.117.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.117.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.117.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.118.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.118.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.118.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.119.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.119.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.119.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.12.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.12.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.12.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.120.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.120.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.120.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.121.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.121.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.121.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.122.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.122.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.122.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.123.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.123.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.123.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.124.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.124.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.124.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.125.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.125.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.125.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.126.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.126.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.126.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.127.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.127.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.127.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.128.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.128.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.128.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.129.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.129.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.129.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.13.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.13.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.13.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.130.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.130.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.130.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.131.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.131.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.131.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.132.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.132.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.132.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.133.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.133.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.133.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.134.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.134.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.134.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.135.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.135.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.135.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.136.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.136.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.136.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.137.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.137.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.137.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.138.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.138.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.138.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.139.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.139.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.139.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.14.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.14.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.14.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.140.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.140.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.140.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.141.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.141.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.141.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.142.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.142.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.142.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.143.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.143.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.143.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.144.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.144.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.144.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.145.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.145.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.145.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.146.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.146.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.146.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.147.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.147.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.147.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.148.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.148.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.148.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.149.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.149.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.149.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.15.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.15.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.15.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.150.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.150.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.150.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.151.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.151.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.151.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.152.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.152.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.152.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.153.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.153.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.153.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.154.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.154.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.154.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.155.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.155.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.155.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.156.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.156.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.156.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.157.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.157.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.157.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.158.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.158.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.158.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.159.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.159.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.159.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.16.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.16.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.16.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.17.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.17.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.17.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.18.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.18.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.18.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.19.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.19.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.19.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.2.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.2.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.2.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.20.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.20.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.20.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.21.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.21.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.21.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.22.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.22.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.22.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.23.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.23.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.23.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.24.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.24.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.24.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.25.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.25.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.25.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.26.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.26.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.26.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.27.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.27.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.27.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.28.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.28.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.28.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.29.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.29.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.29.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.3.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.3.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.3.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.30.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.30.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.30.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.31.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.31.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.31.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.32.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.32.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.32.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.33.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.33.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.33.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.34.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.34.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.34.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.35.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.35.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.35.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.36.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.36.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.36.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.37.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.37.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.37.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.38.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.38.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.38.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.39.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.39.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.39.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.4.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.4.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.4.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.40.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.40.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.40.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.41.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.41.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.41.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.42.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.42.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.42.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.43.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.43.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.43.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.44.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.44.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.44.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.45.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.45.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.45.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.46.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.46.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.46.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.47.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.47.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.47.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.48.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.48.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.48.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.49.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.49.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.49.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.5.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.5.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.5.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.50.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.50.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.50.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.51.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.51.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.51.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.52.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.52.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.52.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.53.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.53.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.53.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.54.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.54.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.54.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.55.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.55.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.55.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.56.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.56.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.56.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.57.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.57.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.57.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.58.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.58.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.58.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.59.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.59.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.59.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.6.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.6.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.6.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.60.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.60.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.60.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.61.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.61.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.61.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.62.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.62.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.62.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.63.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.63.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.63.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.64.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.64.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.64.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.65.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.65.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.65.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.66.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.66.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.66.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.67.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.67.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.67.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.68.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.68.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.68.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.69.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.69.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.69.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.7.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.7.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.7.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.70.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.70.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.70.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.71.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.71.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.71.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.72.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.72.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.72.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.73.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.73.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.73.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.74.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.74.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.74.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.75.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.75.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.75.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.76.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.76.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.76.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.77.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.77.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.77.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.78.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.78.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.78.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.79.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.79.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.79.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.8.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.8.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.8.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.80.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.80.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.80.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.81.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.81.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.81.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.82.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.82.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.82.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.83.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.83.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.83.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.84.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.84.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.84.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.85.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.85.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.85.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.86.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.86.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.86.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.87.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.87.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.87.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.88.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.88.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.88.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.89.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.89.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.89.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.9.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.9.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.9.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.90.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.90.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.90.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.91.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.91.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.91.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.92.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.92.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.92.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.93.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.93.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.93.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.94.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.94.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.94.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.95.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.95.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.95.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.96.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.96.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.96.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.97.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.97.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.97.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.98.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.98.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.98.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.99.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.99.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.experts.99.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.gate.e_score_correction_bias": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.gate.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.shared_experts.down_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.shared_experts.gate_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.mlp.shared_experts.up_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00018-of-00092.safetensors", + "model.layers.17.self_attn.k_norm.weight": "model-00018-of-00092.safetensors", + "model.layers.17.self_attn.k_proj.bias": "model-00018-of-00092.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.self_attn.q_norm.weight": "model-00018-of-00092.safetensors", + "model.layers.17.self_attn.q_proj.bias": "model-00018-of-00092.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.17.self_attn.v_proj.bias": "model-00018-of-00092.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00018-of-00092.safetensors", + "model.layers.18.input_layernorm.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.0.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.0.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.0.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.1.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.1.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.1.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.10.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.10.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.10.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.100.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.100.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.100.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.101.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.101.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.101.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.102.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.102.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.102.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.103.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.103.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.103.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.104.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.104.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.104.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.105.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.105.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.105.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.106.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.106.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.106.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.107.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.107.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.107.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.108.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.108.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.108.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.109.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.109.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.109.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.11.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.11.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.11.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.110.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.110.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.110.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.111.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.111.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.111.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.112.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.112.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.112.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.113.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.113.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.113.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.114.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.114.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.114.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.115.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.115.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.115.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.116.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.116.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.116.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.117.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.117.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.117.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.118.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.118.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.118.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.119.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.119.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.119.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.12.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.12.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.12.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.120.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.120.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.120.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.121.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.121.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.121.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.122.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.122.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.122.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.123.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.123.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.123.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.124.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.124.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.124.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.125.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.125.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.125.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.126.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.126.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.126.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.127.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.127.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.127.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.128.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.128.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.128.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.129.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.129.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.129.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.13.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.13.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.13.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.130.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.130.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.130.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.131.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.131.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.131.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.132.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.132.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.132.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.133.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.133.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.133.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.134.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.134.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.134.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.135.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.135.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.135.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.136.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.136.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.136.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.137.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.137.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.137.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.138.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.138.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.138.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.139.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.139.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.139.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.14.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.14.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.14.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.140.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.140.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.140.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.141.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.141.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.141.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.142.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.142.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.142.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.143.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.143.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.143.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.144.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.144.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.144.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.145.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.145.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.145.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.146.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.146.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.146.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.147.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.147.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.147.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.148.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.148.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.148.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.149.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.149.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.149.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.15.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.15.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.15.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.150.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.150.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.150.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.151.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.151.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.151.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.152.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.152.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.152.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.153.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.153.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.153.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.154.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.154.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.154.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.155.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.155.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.155.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.156.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.156.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.156.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.157.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.157.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.157.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.158.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.158.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.158.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.159.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.159.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.159.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.16.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.16.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.16.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.17.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.17.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.17.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.18.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.18.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.18.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.19.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.19.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.19.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.2.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.2.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.2.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.20.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.20.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.20.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.21.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.21.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.21.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.22.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.22.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.22.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.23.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.23.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.23.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.24.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.24.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.24.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.25.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.25.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.25.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.26.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.26.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.26.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.27.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.27.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.27.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.28.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.28.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.28.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.29.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.29.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.29.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.3.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.3.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.3.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.30.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.30.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.30.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.31.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.31.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.31.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.32.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.32.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.32.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.33.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.33.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.33.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.34.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.34.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.34.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.35.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.35.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.35.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.36.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.36.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.36.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.37.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.37.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.37.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.38.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.38.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.38.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.39.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.39.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.39.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.4.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.4.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.4.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.40.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.40.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.40.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.41.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.41.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.41.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.42.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.42.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.42.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.43.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.43.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.43.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.44.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.44.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.44.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.45.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.45.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.45.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.46.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.46.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.46.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.47.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.47.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.47.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.48.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.48.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.48.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.49.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.49.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.49.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.5.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.5.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.5.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.50.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.50.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.50.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.51.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.51.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.51.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.52.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.52.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.52.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.53.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.53.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.53.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.54.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.54.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.54.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.55.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.55.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.55.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.56.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.56.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.56.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.57.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.57.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.57.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.58.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.58.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.58.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.59.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.59.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.59.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.6.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.6.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.6.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.60.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.60.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.60.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.61.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.61.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.61.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.62.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.62.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.62.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.63.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.63.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.63.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.64.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.64.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.64.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.65.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.65.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.65.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.66.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.66.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.66.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.67.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.67.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.67.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.68.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.68.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.68.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.69.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.69.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.69.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.7.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.7.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.7.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.70.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.70.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.70.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.71.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.71.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.71.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.72.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.72.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.72.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.73.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.73.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.73.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.74.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.74.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.74.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.75.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.75.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.75.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.76.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.76.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.76.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.77.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.77.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.77.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.78.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.78.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.78.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.79.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.79.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.79.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.8.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.8.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.8.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.80.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.80.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.80.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.81.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.81.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.81.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.82.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.82.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.82.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.83.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.83.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.83.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.84.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.84.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.84.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.85.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.85.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.85.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.86.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.86.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.86.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.87.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.87.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.87.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.88.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.88.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.88.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.89.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.89.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.89.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.9.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.9.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.9.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.90.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.90.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.90.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.91.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.91.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.91.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.92.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.92.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.92.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.93.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.93.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.93.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.94.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.94.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.94.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.95.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.95.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.95.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.96.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.96.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.96.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.97.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.97.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.97.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.98.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.98.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.98.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.99.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.99.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.experts.99.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.gate.e_score_correction_bias": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.gate.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.shared_experts.down_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.shared_experts.gate_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.mlp.shared_experts.up_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00019-of-00092.safetensors", + "model.layers.18.self_attn.k_norm.weight": "model-00019-of-00092.safetensors", + "model.layers.18.self_attn.k_proj.bias": "model-00019-of-00092.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.self_attn.q_norm.weight": "model-00019-of-00092.safetensors", + "model.layers.18.self_attn.q_proj.bias": "model-00019-of-00092.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.18.self_attn.v_proj.bias": "model-00019-of-00092.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00019-of-00092.safetensors", + "model.layers.19.input_layernorm.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.0.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.0.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.0.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.1.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.1.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.1.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.10.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.10.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.10.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.100.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.100.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.100.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.101.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.101.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.101.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.102.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.102.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.102.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.103.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.103.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.103.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.104.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.104.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.104.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.105.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.105.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.105.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.106.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.106.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.106.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.107.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.107.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.107.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.108.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.108.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.108.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.109.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.109.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.109.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.11.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.11.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.11.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.110.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.110.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.110.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.111.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.111.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.111.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.112.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.112.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.112.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.113.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.113.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.113.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.114.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.114.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.114.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.115.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.115.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.115.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.116.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.116.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.116.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.117.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.117.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.117.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.118.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.118.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.118.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.119.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.119.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.119.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.12.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.12.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.12.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.120.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.120.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.120.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.121.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.121.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.121.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.122.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.122.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.122.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.123.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.123.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.123.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.124.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.124.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.124.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.125.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.125.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.125.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.126.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.126.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.126.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.127.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.127.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.127.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.128.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.128.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.128.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.129.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.129.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.129.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.13.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.13.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.13.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.130.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.130.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.130.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.131.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.131.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.131.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.132.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.132.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.132.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.133.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.133.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.133.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.134.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.134.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.134.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.135.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.135.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.135.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.136.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.136.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.136.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.137.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.137.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.137.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.138.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.138.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.138.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.139.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.139.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.139.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.14.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.14.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.14.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.140.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.140.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.140.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.141.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.141.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.141.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.142.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.142.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.142.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.143.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.143.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.143.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.144.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.144.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.144.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.145.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.145.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.145.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.146.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.146.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.146.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.147.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.147.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.147.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.148.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.148.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.148.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.149.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.149.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.149.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.15.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.15.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.15.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.150.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.150.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.150.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.151.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.151.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.151.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.152.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.152.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.152.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.153.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.153.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.153.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.154.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.154.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.154.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.155.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.155.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.155.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.156.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.156.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.156.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.157.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.157.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.157.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.158.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.158.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.158.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.159.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.159.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.159.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.16.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.16.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.16.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.17.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.17.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.17.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.18.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.18.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.18.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.19.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.19.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.19.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.2.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.2.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.2.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.20.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.20.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.20.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.21.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.21.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.21.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.22.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.22.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.22.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.23.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.23.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.23.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.24.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.24.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.24.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.25.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.25.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.25.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.26.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.26.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.26.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.27.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.27.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.27.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.28.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.28.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.28.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.29.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.29.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.29.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.3.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.3.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.3.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.30.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.30.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.30.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.31.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.31.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.31.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.32.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.32.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.32.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.33.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.33.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.33.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.34.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.34.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.34.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.35.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.35.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.35.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.36.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.36.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.36.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.37.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.37.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.37.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.38.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.38.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.38.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.39.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.39.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.39.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.4.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.4.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.4.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.40.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.40.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.40.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.41.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.41.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.41.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.42.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.42.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.42.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.43.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.43.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.43.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.44.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.44.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.44.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.45.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.45.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.45.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.46.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.46.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.46.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.47.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.47.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.47.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.48.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.48.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.48.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.49.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.49.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.49.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.5.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.5.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.5.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.50.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.50.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.50.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.51.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.51.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.51.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.52.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.52.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.52.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.53.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.53.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.53.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.54.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.54.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.54.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.55.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.55.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.55.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.56.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.56.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.56.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.57.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.57.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.57.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.58.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.58.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.58.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.59.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.59.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.59.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.6.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.6.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.6.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.60.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.60.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.60.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.61.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.61.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.61.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.62.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.62.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.62.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.63.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.63.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.63.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.64.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.64.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.64.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.65.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.65.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.65.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.66.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.66.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.66.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.67.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.67.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.67.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.68.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.68.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.68.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.69.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.69.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.69.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.7.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.7.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.7.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.70.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.70.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.70.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.71.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.71.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.71.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.72.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.72.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.72.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.73.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.73.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.73.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.74.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.74.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.74.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.75.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.75.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.75.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.76.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.76.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.76.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.77.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.77.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.77.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.78.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.78.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.78.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.79.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.79.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.79.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.8.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.8.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.8.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.80.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.80.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.80.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.81.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.81.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.81.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.82.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.82.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.82.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.83.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.83.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.83.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.84.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.84.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.84.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.85.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.85.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.85.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.86.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.86.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.86.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.87.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.87.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.87.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.88.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.88.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.88.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.89.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.89.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.89.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.9.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.9.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.9.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.90.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.90.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.90.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.91.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.91.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.91.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.92.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.92.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.92.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.93.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.93.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.93.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.94.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.94.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.94.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.95.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.95.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.95.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.96.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.96.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.96.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.97.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.97.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.97.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.98.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.98.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.98.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.99.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.99.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.experts.99.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.gate.e_score_correction_bias": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.gate.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.shared_experts.down_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.shared_experts.gate_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.mlp.shared_experts.up_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00020-of-00092.safetensors", + "model.layers.19.self_attn.k_norm.weight": "model-00020-of-00092.safetensors", + "model.layers.19.self_attn.k_proj.bias": "model-00020-of-00092.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.self_attn.q_norm.weight": "model-00020-of-00092.safetensors", + "model.layers.19.self_attn.q_proj.bias": "model-00020-of-00092.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.19.self_attn.v_proj.bias": "model-00020-of-00092.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00020-of-00092.safetensors", + "model.layers.20.input_layernorm.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.0.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.0.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.0.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.1.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.1.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.1.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.10.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.10.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.10.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.100.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.100.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.100.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.101.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.101.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.101.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.102.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.102.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.102.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.103.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.103.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.103.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.104.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.104.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.104.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.105.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.105.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.105.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.106.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.106.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.106.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.107.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.107.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.107.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.108.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.108.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.108.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.109.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.109.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.109.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.11.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.11.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.11.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.110.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.110.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.110.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.111.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.111.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.111.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.112.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.112.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.112.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.113.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.113.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.113.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.114.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.114.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.114.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.115.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.115.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.115.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.116.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.116.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.116.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.117.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.117.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.117.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.118.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.118.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.118.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.119.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.119.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.119.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.12.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.12.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.12.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.120.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.120.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.120.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.121.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.121.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.121.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.122.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.122.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.122.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.123.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.123.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.123.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.124.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.124.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.124.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.125.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.125.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.125.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.126.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.126.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.126.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.127.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.127.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.127.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.128.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.128.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.128.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.129.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.129.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.129.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.13.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.13.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.13.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.130.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.130.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.130.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.131.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.131.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.131.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.132.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.132.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.132.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.133.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.133.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.133.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.134.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.134.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.134.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.135.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.135.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.135.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.136.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.136.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.136.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.137.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.137.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.137.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.138.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.138.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.138.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.139.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.139.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.139.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.14.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.14.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.14.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.140.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.140.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.140.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.141.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.141.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.141.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.142.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.142.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.142.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.143.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.143.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.143.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.144.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.144.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.144.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.145.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.145.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.145.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.146.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.146.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.146.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.147.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.147.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.147.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.148.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.148.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.148.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.149.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.149.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.149.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.15.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.15.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.15.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.150.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.150.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.150.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.151.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.151.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.151.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.152.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.152.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.152.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.153.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.153.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.153.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.154.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.154.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.154.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.155.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.155.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.155.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.156.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.156.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.156.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.157.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.157.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.157.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.158.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.158.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.158.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.159.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.159.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.159.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.16.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.16.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.16.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.17.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.17.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.17.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.18.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.18.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.18.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.19.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.19.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.19.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.2.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.2.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.2.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.20.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.20.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.20.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.21.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.21.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.21.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.22.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.22.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.22.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.23.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.23.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.23.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.24.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.24.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.24.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.25.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.25.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.25.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.26.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.26.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.26.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.27.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.27.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.27.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.28.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.28.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.28.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.29.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.29.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.29.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.3.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.3.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.3.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.30.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.30.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.30.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.31.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.31.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.31.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.32.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.32.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.32.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.33.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.33.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.33.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.34.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.34.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.34.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.35.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.35.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.35.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.36.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.36.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.36.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.37.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.37.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.37.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.38.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.38.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.38.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.39.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.39.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.39.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.4.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.4.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.4.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.40.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.40.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.40.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.41.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.41.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.41.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.42.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.42.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.42.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.43.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.43.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.43.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.44.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.44.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.44.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.45.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.45.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.45.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.46.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.46.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.46.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.47.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.47.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.47.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.48.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.48.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.48.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.49.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.49.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.49.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.5.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.5.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.5.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.50.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.50.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.50.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.51.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.51.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.51.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.52.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.52.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.52.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.53.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.53.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.53.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.54.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.54.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.54.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.55.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.55.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.55.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.56.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.56.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.56.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.57.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.57.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.57.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.58.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.58.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.58.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.59.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.59.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.59.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.6.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.6.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.6.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.60.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.60.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.60.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.61.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.61.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.61.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.62.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.62.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.62.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.63.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.63.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.63.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.64.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.64.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.64.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.65.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.65.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.65.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.66.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.66.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.66.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.67.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.67.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.67.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.68.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.68.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.68.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.69.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.69.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.69.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.7.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.7.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.7.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.70.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.70.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.70.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.71.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.71.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.71.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.72.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.72.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.72.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.73.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.73.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.73.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.74.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.74.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.74.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.75.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.75.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.75.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.76.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.76.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.76.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.77.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.77.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.77.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.78.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.78.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.78.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.79.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.79.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.79.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.8.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.8.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.8.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.80.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.80.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.80.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.81.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.81.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.81.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.82.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.82.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.82.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.83.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.83.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.83.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.84.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.84.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.84.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.85.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.85.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.85.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.86.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.86.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.86.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.87.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.87.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.87.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.88.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.88.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.88.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.89.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.89.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.89.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.9.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.9.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.9.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.90.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.90.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.90.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.91.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.91.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.91.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.92.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.92.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.92.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.93.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.93.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.93.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.94.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.94.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.94.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.95.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.95.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.95.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.96.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.96.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.96.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.97.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.97.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.97.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.98.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.98.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.98.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.99.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.99.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.experts.99.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.gate.e_score_correction_bias": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.gate.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.shared_experts.down_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.shared_experts.gate_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.mlp.shared_experts.up_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00021-of-00092.safetensors", + "model.layers.20.self_attn.k_norm.weight": "model-00021-of-00092.safetensors", + "model.layers.20.self_attn.k_proj.bias": "model-00021-of-00092.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.self_attn.q_norm.weight": "model-00021-of-00092.safetensors", + "model.layers.20.self_attn.q_proj.bias": "model-00021-of-00092.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.20.self_attn.v_proj.bias": "model-00021-of-00092.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00021-of-00092.safetensors", + "model.layers.21.input_layernorm.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.0.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.0.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.0.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.1.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.1.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.1.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.10.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.10.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.10.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.100.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.100.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.100.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.101.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.101.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.101.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.102.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.102.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.102.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.103.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.103.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.103.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.104.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.104.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.104.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.105.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.105.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.105.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.106.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.106.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.106.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.107.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.107.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.107.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.108.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.108.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.108.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.109.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.109.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.109.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.11.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.11.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.11.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.110.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.110.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.110.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.111.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.111.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.111.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.112.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.112.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.112.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.113.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.113.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.113.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.114.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.114.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.114.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.115.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.115.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.115.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.116.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.116.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.116.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.117.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.117.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.117.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.118.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.118.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.118.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.119.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.119.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.119.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.12.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.12.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.12.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.120.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.120.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.120.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.121.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.121.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.121.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.122.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.122.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.122.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.123.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.123.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.123.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.124.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.124.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.124.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.125.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.125.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.125.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.126.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.126.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.126.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.127.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.127.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.127.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.128.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.128.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.128.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.129.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.129.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.129.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.13.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.13.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.13.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.130.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.130.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.130.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.131.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.131.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.131.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.132.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.132.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.132.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.133.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.133.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.133.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.134.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.134.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.134.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.135.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.135.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.135.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.136.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.136.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.136.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.137.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.137.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.137.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.138.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.138.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.138.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.139.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.139.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.139.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.14.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.14.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.14.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.140.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.140.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.140.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.141.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.141.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.141.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.142.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.142.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.142.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.143.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.143.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.143.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.144.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.144.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.144.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.145.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.145.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.145.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.146.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.146.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.146.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.147.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.147.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.147.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.148.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.148.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.148.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.149.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.149.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.149.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.15.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.15.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.15.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.150.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.150.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.150.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.151.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.151.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.151.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.152.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.152.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.152.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.153.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.153.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.153.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.154.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.154.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.154.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.155.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.155.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.155.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.156.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.156.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.156.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.157.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.157.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.157.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.158.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.158.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.158.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.159.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.159.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.159.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.16.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.16.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.16.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.17.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.17.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.17.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.18.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.18.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.18.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.19.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.19.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.19.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.2.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.2.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.2.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.20.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.20.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.20.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.21.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.21.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.21.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.22.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.22.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.22.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.23.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.23.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.23.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.24.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.24.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.24.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.25.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.25.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.25.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.26.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.26.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.26.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.27.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.27.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.27.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.28.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.28.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.28.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.29.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.29.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.29.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.3.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.3.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.3.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.30.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.30.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.30.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.31.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.31.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.31.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.32.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.32.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.32.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.33.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.33.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.33.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.34.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.34.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.34.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.35.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.35.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.35.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.36.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.36.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.36.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.37.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.37.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.37.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.38.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.38.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.38.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.39.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.39.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.39.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.4.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.4.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.4.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.40.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.40.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.40.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.41.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.41.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.41.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.42.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.42.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.42.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.43.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.43.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.43.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.44.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.44.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.44.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.45.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.45.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.45.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.46.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.46.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.46.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.47.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.47.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.47.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.48.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.48.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.48.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.49.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.49.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.49.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.5.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.5.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.5.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.50.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.50.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.50.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.51.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.51.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.51.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.52.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.52.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.52.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.53.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.53.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.53.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.54.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.54.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.54.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.55.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.55.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.55.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.56.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.56.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.56.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.57.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.57.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.57.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.58.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.58.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.58.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.59.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.59.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.59.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.6.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.6.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.6.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.60.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.60.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.60.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.61.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.61.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.61.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.62.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.62.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.62.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.63.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.63.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.63.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.64.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.64.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.64.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.65.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.65.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.65.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.66.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.66.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.66.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.67.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.67.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.67.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.68.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.68.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.68.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.69.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.69.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.69.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.7.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.7.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.7.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.70.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.70.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.70.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.71.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.71.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.71.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.72.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.72.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.72.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.73.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.73.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.73.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.74.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.74.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.74.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.75.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.75.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.75.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.76.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.76.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.76.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.77.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.77.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.77.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.78.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.78.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.78.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.79.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.79.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.79.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.8.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.8.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.8.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.80.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.80.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.80.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.81.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.81.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.81.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.82.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.82.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.82.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.83.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.83.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.83.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.84.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.84.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.84.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.85.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.85.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.85.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.86.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.86.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.86.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.87.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.87.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.87.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.88.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.88.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.88.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.89.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.89.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.89.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.9.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.9.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.9.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.90.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.90.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.90.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.91.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.91.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.91.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.92.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.92.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.92.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.93.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.93.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.93.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.94.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.94.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.94.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.95.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.95.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.95.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.96.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.96.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.96.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.97.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.97.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.97.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.98.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.98.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.98.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.99.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.99.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.experts.99.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.gate.e_score_correction_bias": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.gate.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.shared_experts.down_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.shared_experts.gate_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.mlp.shared_experts.up_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00022-of-00092.safetensors", + "model.layers.21.self_attn.k_norm.weight": "model-00022-of-00092.safetensors", + "model.layers.21.self_attn.k_proj.bias": "model-00022-of-00092.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.self_attn.q_norm.weight": "model-00022-of-00092.safetensors", + "model.layers.21.self_attn.q_proj.bias": "model-00022-of-00092.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.21.self_attn.v_proj.bias": "model-00022-of-00092.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00022-of-00092.safetensors", + "model.layers.22.input_layernorm.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.0.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.0.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.0.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.1.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.1.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.1.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.10.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.10.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.10.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.100.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.100.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.100.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.101.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.101.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.101.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.102.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.102.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.102.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.103.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.103.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.103.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.104.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.104.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.104.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.105.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.105.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.105.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.106.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.106.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.106.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.107.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.107.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.107.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.108.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.108.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.108.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.109.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.109.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.109.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.11.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.11.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.11.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.110.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.110.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.110.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.111.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.111.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.111.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.112.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.112.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.112.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.113.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.113.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.113.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.114.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.114.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.114.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.115.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.115.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.115.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.116.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.116.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.116.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.117.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.117.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.117.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.118.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.118.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.118.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.119.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.119.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.119.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.12.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.12.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.12.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.120.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.120.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.120.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.121.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.121.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.121.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.122.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.122.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.122.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.123.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.123.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.123.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.124.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.124.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.124.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.125.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.125.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.125.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.126.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.126.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.126.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.127.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.127.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.127.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.128.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.128.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.128.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.129.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.129.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.129.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.13.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.13.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.13.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.130.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.130.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.130.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.131.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.131.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.131.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.132.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.132.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.132.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.133.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.133.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.133.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.134.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.134.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.134.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.135.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.135.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.135.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.136.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.136.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.136.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.137.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.137.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.137.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.138.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.138.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.138.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.139.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.139.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.139.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.14.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.14.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.14.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.140.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.140.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.140.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.141.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.141.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.141.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.142.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.142.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.142.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.143.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.143.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.143.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.144.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.144.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.144.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.145.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.145.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.145.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.146.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.146.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.146.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.147.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.147.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.147.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.148.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.148.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.148.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.149.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.149.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.149.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.15.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.15.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.15.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.150.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.150.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.150.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.151.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.151.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.151.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.152.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.152.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.152.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.153.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.153.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.153.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.154.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.154.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.154.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.155.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.155.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.155.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.156.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.156.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.156.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.157.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.157.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.157.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.158.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.158.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.158.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.159.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.159.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.159.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.16.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.16.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.16.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.17.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.17.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.17.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.18.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.18.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.18.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.19.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.19.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.19.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.2.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.2.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.2.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.20.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.20.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.20.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.21.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.21.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.21.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.22.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.22.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.22.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.23.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.23.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.23.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.24.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.24.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.24.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.25.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.25.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.25.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.26.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.26.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.26.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.27.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.27.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.27.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.28.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.28.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.28.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.29.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.29.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.29.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.3.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.3.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.3.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.30.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.30.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.30.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.31.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.31.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.31.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.32.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.32.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.32.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.33.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.33.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.33.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.34.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.34.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.34.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.35.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.35.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.35.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.36.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.36.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.36.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.37.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.37.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.37.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.38.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.38.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.38.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.39.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.39.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.39.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.4.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.4.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.4.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.40.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.40.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.40.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.41.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.41.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.41.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.42.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.42.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.42.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.43.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.43.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.43.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.44.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.44.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.44.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.45.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.45.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.45.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.46.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.46.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.46.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.47.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.47.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.47.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.48.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.48.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.48.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.49.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.49.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.49.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.5.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.5.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.5.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.50.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.50.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.50.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.51.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.51.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.51.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.52.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.52.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.52.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.53.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.53.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.53.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.54.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.54.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.54.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.55.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.55.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.55.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.56.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.56.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.56.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.57.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.57.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.57.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.58.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.58.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.58.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.59.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.59.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.59.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.6.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.6.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.6.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.60.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.60.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.60.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.61.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.61.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.61.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.62.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.62.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.62.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.63.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.63.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.63.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.64.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.64.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.64.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.65.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.65.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.65.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.66.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.66.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.66.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.67.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.67.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.67.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.68.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.68.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.68.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.69.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.69.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.69.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.7.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.7.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.7.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.70.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.70.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.70.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.71.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.71.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.71.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.72.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.72.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.72.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.73.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.73.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.73.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.74.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.74.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.74.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.75.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.75.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.75.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.76.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.76.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.76.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.77.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.77.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.77.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.78.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.78.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.78.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.79.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.79.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.79.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.8.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.8.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.8.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.80.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.80.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.80.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.81.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.81.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.81.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.82.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.82.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.82.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.83.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.83.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.83.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.84.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.84.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.84.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.85.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.85.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.85.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.86.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.86.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.86.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.87.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.87.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.87.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.88.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.88.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.88.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.89.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.89.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.89.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.9.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.9.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.9.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.90.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.90.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.90.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.91.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.91.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.91.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.92.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.92.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.92.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.93.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.93.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.93.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.94.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.94.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.94.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.95.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.95.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.95.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.96.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.96.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.96.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.97.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.97.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.97.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.98.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.98.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.98.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.99.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.99.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.experts.99.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.gate.e_score_correction_bias": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.gate.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.shared_experts.down_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.shared_experts.gate_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.mlp.shared_experts.up_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00023-of-00092.safetensors", + "model.layers.22.self_attn.k_norm.weight": "model-00023-of-00092.safetensors", + "model.layers.22.self_attn.k_proj.bias": "model-00023-of-00092.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.self_attn.q_norm.weight": "model-00023-of-00092.safetensors", + "model.layers.22.self_attn.q_proj.bias": "model-00023-of-00092.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.22.self_attn.v_proj.bias": "model-00023-of-00092.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00023-of-00092.safetensors", + "model.layers.23.input_layernorm.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.0.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.0.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.0.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.1.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.1.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.1.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.10.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.10.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.10.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.100.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.100.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.100.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.101.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.101.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.101.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.102.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.102.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.102.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.103.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.103.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.103.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.104.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.104.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.104.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.105.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.105.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.105.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.106.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.106.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.106.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.107.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.107.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.107.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.108.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.108.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.108.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.109.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.109.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.109.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.11.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.11.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.11.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.110.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.110.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.110.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.111.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.111.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.111.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.112.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.112.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.112.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.113.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.113.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.113.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.114.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.114.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.114.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.115.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.115.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.115.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.116.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.116.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.116.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.117.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.117.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.117.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.118.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.118.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.118.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.119.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.119.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.119.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.12.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.12.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.12.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.120.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.120.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.120.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.121.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.121.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.121.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.122.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.122.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.122.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.123.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.123.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.123.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.124.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.124.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.124.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.125.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.125.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.125.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.126.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.126.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.126.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.127.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.127.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.127.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.128.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.128.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.128.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.129.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.129.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.129.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.13.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.13.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.13.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.130.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.130.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.130.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.131.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.131.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.131.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.132.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.132.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.132.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.133.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.133.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.133.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.134.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.134.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.134.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.135.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.135.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.135.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.136.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.136.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.136.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.137.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.137.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.137.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.138.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.138.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.138.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.139.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.139.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.139.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.14.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.14.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.14.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.140.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.140.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.140.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.141.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.141.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.141.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.142.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.142.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.142.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.143.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.143.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.143.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.144.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.144.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.144.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.145.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.145.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.145.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.146.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.146.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.146.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.147.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.147.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.147.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.148.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.148.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.148.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.149.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.149.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.149.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.15.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.15.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.15.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.150.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.150.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.150.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.151.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.151.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.151.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.152.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.152.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.152.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.153.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.153.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.153.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.154.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.154.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.154.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.155.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.155.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.155.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.156.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.156.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.156.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.157.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.157.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.157.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.158.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.158.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.158.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.159.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.159.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.159.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.16.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.16.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.16.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.17.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.17.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.17.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.18.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.18.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.18.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.19.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.19.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.19.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.2.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.2.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.2.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.20.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.20.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.20.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.21.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.21.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.21.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.22.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.22.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.22.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.23.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.23.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.23.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.24.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.24.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.24.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.25.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.25.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.25.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.26.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.26.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.26.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.27.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.27.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.27.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.28.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.28.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.28.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.29.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.29.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.29.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.3.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.3.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.3.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.30.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.30.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.30.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.31.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.31.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.31.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.32.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.32.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.32.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.33.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.33.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.33.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.34.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.34.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.34.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.35.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.35.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.35.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.36.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.36.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.36.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.37.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.37.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.37.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.38.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.38.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.38.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.39.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.39.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.39.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.4.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.4.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.4.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.40.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.40.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.40.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.41.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.41.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.41.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.42.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.42.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.42.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.43.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.43.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.43.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.44.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.44.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.44.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.45.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.45.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.45.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.46.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.46.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.46.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.47.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.47.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.47.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.48.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.48.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.48.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.49.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.49.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.49.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.5.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.5.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.5.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.50.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.50.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.50.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.51.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.51.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.51.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.52.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.52.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.52.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.53.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.53.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.53.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.54.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.54.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.54.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.55.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.55.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.55.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.56.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.56.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.56.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.57.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.57.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.57.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.58.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.58.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.58.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.59.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.59.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.59.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.6.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.6.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.6.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.60.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.60.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.60.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.61.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.61.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.61.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.62.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.62.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.62.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.63.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.63.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.63.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.64.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.64.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.64.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.65.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.65.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.65.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.66.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.66.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.66.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.67.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.67.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.67.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.68.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.68.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.68.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.69.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.69.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.69.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.7.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.7.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.7.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.70.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.70.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.70.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.71.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.71.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.71.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.72.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.72.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.72.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.73.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.73.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.73.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.74.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.74.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.74.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.75.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.75.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.75.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.76.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.76.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.76.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.77.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.77.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.77.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.78.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.78.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.78.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.79.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.79.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.79.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.8.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.8.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.8.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.80.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.80.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.80.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.81.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.81.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.81.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.82.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.82.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.82.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.83.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.83.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.83.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.84.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.84.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.84.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.85.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.85.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.85.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.86.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.86.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.86.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.87.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.87.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.87.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.88.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.88.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.88.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.89.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.89.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.89.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.9.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.9.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.9.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.90.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.90.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.90.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.91.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.91.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.91.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.92.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.92.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.92.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.93.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.93.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.93.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.94.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.94.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.94.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.95.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.95.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.95.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.96.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.96.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.96.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.97.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.97.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.97.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.98.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.98.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.98.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.99.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.99.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.experts.99.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.gate.e_score_correction_bias": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.gate.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.shared_experts.down_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.shared_experts.gate_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.mlp.shared_experts.up_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00024-of-00092.safetensors", + "model.layers.23.self_attn.k_norm.weight": "model-00024-of-00092.safetensors", + "model.layers.23.self_attn.k_proj.bias": "model-00024-of-00092.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.self_attn.q_norm.weight": "model-00024-of-00092.safetensors", + "model.layers.23.self_attn.q_proj.bias": "model-00024-of-00092.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.23.self_attn.v_proj.bias": "model-00024-of-00092.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00024-of-00092.safetensors", + "model.layers.24.input_layernorm.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.0.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.0.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.0.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.1.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.1.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.1.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.10.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.10.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.10.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.100.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.100.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.100.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.101.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.101.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.101.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.102.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.102.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.102.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.103.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.103.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.103.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.104.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.104.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.104.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.105.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.105.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.105.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.106.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.106.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.106.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.107.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.107.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.107.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.108.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.108.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.108.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.109.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.109.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.109.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.11.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.11.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.11.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.110.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.110.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.110.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.111.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.111.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.111.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.112.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.112.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.112.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.113.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.113.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.113.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.114.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.114.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.114.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.115.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.115.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.115.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.116.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.116.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.116.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.117.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.117.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.117.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.118.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.118.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.118.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.119.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.119.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.119.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.12.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.12.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.12.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.120.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.120.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.120.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.121.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.121.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.121.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.122.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.122.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.122.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.123.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.123.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.123.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.124.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.124.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.124.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.125.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.125.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.125.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.126.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.126.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.126.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.127.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.127.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.127.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.128.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.128.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.128.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.129.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.129.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.129.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.13.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.13.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.13.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.130.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.130.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.130.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.131.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.131.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.131.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.132.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.132.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.132.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.133.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.133.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.133.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.134.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.134.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.134.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.135.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.135.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.135.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.136.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.136.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.136.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.137.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.137.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.137.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.138.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.138.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.138.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.139.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.139.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.139.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.14.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.14.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.14.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.140.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.140.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.140.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.141.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.141.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.141.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.142.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.142.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.142.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.143.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.143.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.143.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.144.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.144.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.144.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.145.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.145.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.145.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.146.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.146.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.146.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.147.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.147.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.147.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.148.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.148.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.148.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.149.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.149.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.149.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.15.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.15.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.15.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.150.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.150.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.150.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.151.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.151.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.151.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.152.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.152.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.152.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.153.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.153.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.153.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.154.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.154.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.154.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.155.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.155.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.155.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.156.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.156.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.156.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.157.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.157.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.157.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.158.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.158.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.158.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.159.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.159.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.159.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.16.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.16.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.16.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.17.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.17.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.17.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.18.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.18.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.18.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.19.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.19.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.19.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.2.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.2.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.2.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.20.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.20.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.20.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.21.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.21.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.21.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.22.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.22.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.22.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.23.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.23.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.23.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.24.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.24.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.24.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.25.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.25.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.25.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.26.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.26.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.26.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.27.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.27.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.27.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.28.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.28.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.28.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.29.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.29.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.29.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.3.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.3.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.3.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.30.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.30.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.30.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.31.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.31.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.31.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.32.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.32.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.32.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.33.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.33.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.33.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.34.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.34.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.34.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.35.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.35.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.35.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.36.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.36.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.36.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.37.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.37.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.37.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.38.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.38.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.38.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.39.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.39.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.39.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.4.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.4.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.4.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.40.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.40.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.40.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.41.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.41.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.41.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.42.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.42.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.42.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.43.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.43.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.43.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.44.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.44.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.44.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.45.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.45.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.45.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.46.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.46.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.46.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.47.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.47.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.47.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.48.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.48.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.48.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.49.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.49.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.49.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.5.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.5.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.5.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.50.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.50.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.50.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.51.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.51.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.51.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.52.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.52.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.52.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.53.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.53.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.53.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.54.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.54.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.54.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.55.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.55.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.55.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.56.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.56.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.56.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.57.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.57.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.57.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.58.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.58.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.58.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.59.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.59.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.59.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.6.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.6.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.6.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.60.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.60.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.60.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.61.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.61.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.61.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.62.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.62.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.62.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.63.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.63.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.63.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.64.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.64.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.64.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.65.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.65.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.65.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.66.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.66.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.66.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.67.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.67.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.67.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.68.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.68.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.68.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.69.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.69.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.69.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.7.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.7.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.7.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.70.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.70.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.70.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.71.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.71.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.71.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.72.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.72.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.72.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.73.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.73.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.73.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.74.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.74.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.74.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.75.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.75.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.75.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.76.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.76.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.76.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.77.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.77.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.77.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.78.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.78.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.78.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.79.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.79.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.79.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.8.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.8.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.8.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.80.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.80.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.80.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.81.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.81.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.81.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.82.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.82.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.82.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.83.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.83.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.83.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.84.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.84.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.84.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.85.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.85.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.85.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.86.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.86.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.86.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.87.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.87.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.87.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.88.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.88.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.88.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.89.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.89.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.89.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.9.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.9.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.9.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.90.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.90.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.90.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.91.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.91.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.91.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.92.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.92.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.92.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.93.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.93.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.93.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.94.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.94.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.94.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.95.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.95.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.95.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.96.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.96.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.96.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.97.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.97.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.97.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.98.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.98.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.98.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.99.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.99.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.experts.99.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.gate.e_score_correction_bias": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.gate.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.shared_experts.down_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.shared_experts.gate_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.mlp.shared_experts.up_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00025-of-00092.safetensors", + "model.layers.24.self_attn.k_norm.weight": "model-00025-of-00092.safetensors", + "model.layers.24.self_attn.k_proj.bias": "model-00025-of-00092.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.self_attn.q_norm.weight": "model-00025-of-00092.safetensors", + "model.layers.24.self_attn.q_proj.bias": "model-00025-of-00092.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.24.self_attn.v_proj.bias": "model-00025-of-00092.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00025-of-00092.safetensors", + "model.layers.25.input_layernorm.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.0.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.0.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.0.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.1.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.1.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.1.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.10.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.10.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.10.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.100.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.100.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.100.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.101.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.101.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.101.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.102.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.102.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.102.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.103.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.103.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.103.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.104.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.104.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.104.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.105.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.105.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.105.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.106.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.106.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.106.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.107.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.107.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.107.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.108.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.108.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.108.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.109.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.109.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.109.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.11.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.11.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.11.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.110.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.110.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.110.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.111.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.111.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.111.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.112.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.112.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.112.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.113.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.113.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.113.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.114.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.114.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.114.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.115.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.115.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.115.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.116.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.116.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.116.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.117.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.117.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.117.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.118.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.118.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.118.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.119.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.119.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.119.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.12.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.12.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.12.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.120.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.120.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.120.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.121.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.121.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.121.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.122.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.122.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.122.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.123.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.123.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.123.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.124.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.124.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.124.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.125.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.125.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.125.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.126.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.126.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.126.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.127.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.127.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.127.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.128.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.128.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.128.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.129.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.129.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.129.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.13.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.13.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.13.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.130.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.130.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.130.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.131.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.131.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.131.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.132.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.132.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.132.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.133.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.133.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.133.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.134.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.134.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.134.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.135.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.135.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.135.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.136.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.136.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.136.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.137.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.137.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.137.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.138.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.138.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.138.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.139.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.139.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.139.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.14.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.14.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.14.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.140.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.140.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.140.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.141.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.141.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.141.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.142.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.142.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.142.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.143.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.143.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.143.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.144.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.144.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.144.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.145.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.145.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.145.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.146.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.146.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.146.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.147.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.147.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.147.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.148.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.148.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.148.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.149.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.149.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.149.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.15.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.15.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.15.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.150.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.150.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.150.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.151.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.151.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.151.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.152.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.152.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.152.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.153.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.153.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.153.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.154.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.154.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.154.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.155.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.155.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.155.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.156.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.156.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.156.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.157.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.157.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.157.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.158.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.158.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.158.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.159.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.159.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.159.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.16.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.16.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.16.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.17.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.17.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.17.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.18.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.18.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.18.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.19.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.19.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.19.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.2.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.2.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.2.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.20.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.20.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.20.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.21.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.21.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.21.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.22.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.22.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.22.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.23.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.23.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.23.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.24.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.24.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.24.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.25.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.25.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.25.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.26.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.26.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.26.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.27.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.27.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.27.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.28.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.28.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.28.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.29.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.29.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.29.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.3.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.3.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.3.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.30.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.30.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.30.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.31.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.31.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.31.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.32.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.32.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.32.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.33.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.33.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.33.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.34.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.34.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.34.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.35.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.35.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.35.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.36.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.36.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.36.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.37.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.37.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.37.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.38.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.38.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.38.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.39.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.39.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.39.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.4.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.4.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.4.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.40.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.40.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.40.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.41.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.41.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.41.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.42.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.42.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.42.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.43.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.43.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.43.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.44.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.44.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.44.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.45.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.45.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.45.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.46.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.46.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.46.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.47.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.47.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.47.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.48.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.48.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.48.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.49.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.49.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.49.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.5.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.5.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.5.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.50.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.50.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.50.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.51.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.51.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.51.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.52.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.52.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.52.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.53.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.53.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.53.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.54.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.54.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.54.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.55.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.55.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.55.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.56.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.56.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.56.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.57.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.57.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.57.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.58.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.58.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.58.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.59.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.59.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.59.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.6.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.6.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.6.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.60.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.60.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.60.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.61.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.61.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.61.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.62.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.62.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.62.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.63.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.63.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.63.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.64.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.64.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.64.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.65.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.65.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.65.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.66.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.66.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.66.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.67.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.67.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.67.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.68.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.68.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.68.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.69.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.69.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.69.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.7.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.7.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.7.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.70.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.70.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.70.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.71.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.71.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.71.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.72.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.72.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.72.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.73.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.73.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.73.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.74.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.74.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.74.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.75.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.75.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.75.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.76.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.76.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.76.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.77.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.77.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.77.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.78.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.78.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.78.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.79.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.79.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.79.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.8.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.8.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.8.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.80.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.80.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.80.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.81.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.81.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.81.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.82.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.82.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.82.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.83.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.83.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.83.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.84.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.84.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.84.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.85.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.85.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.85.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.86.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.86.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.86.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.87.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.87.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.87.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.88.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.88.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.88.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.89.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.89.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.89.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.9.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.9.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.9.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.90.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.90.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.90.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.91.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.91.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.91.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.92.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.92.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.92.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.93.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.93.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.93.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.94.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.94.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.94.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.95.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.95.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.95.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.96.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.96.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.96.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.97.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.97.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.97.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.98.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.98.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.98.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.99.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.99.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.experts.99.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.gate.e_score_correction_bias": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.gate.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.shared_experts.down_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.shared_experts.gate_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.mlp.shared_experts.up_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00026-of-00092.safetensors", + "model.layers.25.self_attn.k_norm.weight": "model-00026-of-00092.safetensors", + "model.layers.25.self_attn.k_proj.bias": "model-00026-of-00092.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.self_attn.q_norm.weight": "model-00026-of-00092.safetensors", + "model.layers.25.self_attn.q_proj.bias": "model-00026-of-00092.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.25.self_attn.v_proj.bias": "model-00026-of-00092.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00026-of-00092.safetensors", + "model.layers.26.input_layernorm.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.0.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.0.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.0.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.1.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.1.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.1.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.10.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.10.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.10.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.100.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.100.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.100.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.101.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.101.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.101.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.102.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.102.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.102.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.103.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.103.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.103.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.104.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.104.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.104.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.105.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.105.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.105.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.106.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.106.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.106.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.107.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.107.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.107.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.108.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.108.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.108.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.109.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.109.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.109.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.11.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.11.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.11.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.110.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.110.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.110.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.111.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.111.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.111.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.112.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.112.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.112.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.113.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.113.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.113.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.114.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.114.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.114.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.115.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.115.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.115.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.116.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.116.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.116.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.117.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.117.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.117.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.118.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.118.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.118.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.119.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.119.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.119.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.12.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.12.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.12.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.120.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.120.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.120.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.121.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.121.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.121.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.122.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.122.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.122.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.123.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.123.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.123.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.124.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.124.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.124.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.125.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.125.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.125.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.126.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.126.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.126.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.127.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.127.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.127.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.128.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.128.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.128.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.129.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.129.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.129.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.13.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.13.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.13.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.130.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.130.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.130.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.131.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.131.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.131.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.132.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.132.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.132.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.133.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.133.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.133.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.134.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.134.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.134.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.135.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.135.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.135.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.136.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.136.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.136.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.137.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.137.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.137.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.138.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.138.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.138.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.139.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.139.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.139.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.14.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.14.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.14.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.140.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.140.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.140.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.141.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.141.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.141.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.142.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.142.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.142.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.143.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.143.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.143.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.144.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.144.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.144.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.145.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.145.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.145.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.146.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.146.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.146.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.147.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.147.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.147.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.148.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.148.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.148.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.149.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.149.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.149.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.15.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.15.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.15.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.150.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.150.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.150.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.151.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.151.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.151.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.152.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.152.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.152.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.153.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.153.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.153.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.154.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.154.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.154.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.155.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.155.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.155.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.156.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.156.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.156.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.157.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.157.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.157.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.158.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.158.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.158.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.159.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.159.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.159.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.16.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.16.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.16.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.17.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.17.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.17.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.18.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.18.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.18.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.19.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.19.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.19.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.2.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.2.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.2.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.20.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.20.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.20.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.21.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.21.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.21.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.22.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.22.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.22.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.23.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.23.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.23.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.24.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.24.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.24.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.25.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.25.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.25.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.26.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.26.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.26.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.27.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.27.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.27.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.28.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.28.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.28.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.29.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.29.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.29.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.3.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.3.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.3.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.30.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.30.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.30.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.31.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.31.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.31.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.32.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.32.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.32.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.33.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.33.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.33.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.34.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.34.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.34.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.35.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.35.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.35.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.36.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.36.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.36.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.37.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.37.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.37.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.38.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.38.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.38.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.39.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.39.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.39.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.4.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.4.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.4.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.40.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.40.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.40.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.41.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.41.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.41.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.42.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.42.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.42.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.43.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.43.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.43.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.44.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.44.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.44.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.45.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.45.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.45.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.46.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.46.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.46.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.47.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.47.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.47.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.48.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.48.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.48.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.49.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.49.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.49.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.5.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.5.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.5.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.50.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.50.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.50.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.51.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.51.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.51.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.52.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.52.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.52.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.53.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.53.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.53.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.54.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.54.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.54.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.55.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.55.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.55.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.56.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.56.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.56.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.57.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.57.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.57.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.58.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.58.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.58.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.59.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.59.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.59.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.6.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.6.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.6.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.60.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.60.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.60.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.61.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.61.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.61.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.62.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.62.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.62.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.63.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.63.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.63.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.64.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.64.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.64.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.65.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.65.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.65.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.66.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.66.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.66.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.67.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.67.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.67.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.68.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.68.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.68.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.69.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.69.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.69.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.7.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.7.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.7.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.70.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.70.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.70.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.71.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.71.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.71.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.72.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.72.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.72.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.73.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.73.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.73.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.74.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.74.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.74.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.75.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.75.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.75.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.76.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.76.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.76.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.77.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.77.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.77.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.78.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.78.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.78.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.79.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.79.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.79.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.8.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.8.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.8.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.80.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.80.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.80.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.81.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.81.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.81.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.82.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.82.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.82.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.83.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.83.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.83.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.84.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.84.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.84.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.85.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.85.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.85.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.86.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.86.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.86.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.87.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.87.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.87.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.88.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.88.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.88.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.89.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.89.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.89.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.9.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.9.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.9.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.90.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.90.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.90.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.91.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.91.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.91.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.92.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.92.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.92.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.93.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.93.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.93.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.94.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.94.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.94.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.95.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.95.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.95.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.96.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.96.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.96.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.97.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.97.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.97.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.98.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.98.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.98.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.99.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.99.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.experts.99.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.gate.e_score_correction_bias": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.gate.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.shared_experts.down_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.shared_experts.gate_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.mlp.shared_experts.up_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00027-of-00092.safetensors", + "model.layers.26.self_attn.k_norm.weight": "model-00027-of-00092.safetensors", + "model.layers.26.self_attn.k_proj.bias": "model-00027-of-00092.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.self_attn.q_norm.weight": "model-00027-of-00092.safetensors", + "model.layers.26.self_attn.q_proj.bias": "model-00027-of-00092.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.26.self_attn.v_proj.bias": "model-00027-of-00092.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00027-of-00092.safetensors", + "model.layers.27.input_layernorm.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.0.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.0.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.0.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.1.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.1.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.1.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.10.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.10.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.10.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.100.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.100.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.100.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.101.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.101.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.101.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.102.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.102.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.102.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.103.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.103.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.103.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.104.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.104.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.104.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.105.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.105.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.105.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.106.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.106.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.106.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.107.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.107.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.107.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.108.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.108.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.108.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.109.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.109.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.109.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.11.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.11.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.11.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.110.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.110.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.110.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.111.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.111.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.111.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.112.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.112.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.112.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.113.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.113.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.113.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.114.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.114.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.114.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.115.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.115.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.115.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.116.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.116.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.116.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.117.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.117.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.117.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.118.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.118.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.118.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.119.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.119.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.119.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.12.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.12.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.12.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.120.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.120.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.120.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.121.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.121.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.121.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.122.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.122.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.122.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.123.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.123.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.123.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.124.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.124.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.124.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.125.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.125.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.125.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.126.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.126.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.126.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.127.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.127.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.127.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.128.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.128.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.128.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.129.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.129.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.129.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.13.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.13.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.13.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.130.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.130.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.130.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.131.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.131.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.131.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.132.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.132.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.132.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.133.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.133.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.133.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.134.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.134.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.134.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.135.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.135.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.135.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.136.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.136.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.136.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.137.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.137.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.137.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.138.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.138.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.138.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.139.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.139.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.139.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.14.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.14.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.14.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.140.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.140.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.140.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.141.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.141.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.141.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.142.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.142.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.142.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.143.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.143.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.143.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.144.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.144.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.144.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.145.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.145.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.145.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.146.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.146.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.146.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.147.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.147.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.147.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.148.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.148.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.148.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.149.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.149.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.149.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.15.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.15.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.15.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.150.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.150.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.150.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.151.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.151.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.151.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.152.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.152.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.152.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.153.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.153.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.153.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.154.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.154.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.154.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.155.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.155.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.155.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.156.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.156.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.156.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.157.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.157.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.157.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.158.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.158.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.158.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.159.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.159.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.159.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.16.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.16.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.16.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.17.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.17.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.17.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.18.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.18.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.18.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.19.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.19.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.19.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.2.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.2.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.2.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.20.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.20.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.20.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.21.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.21.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.21.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.22.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.22.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.22.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.23.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.23.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.23.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.24.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.24.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.24.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.25.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.25.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.25.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.26.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.26.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.26.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.27.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.27.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.27.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.28.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.28.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.28.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.29.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.29.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.29.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.3.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.3.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.3.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.30.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.30.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.30.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.31.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.31.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.31.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.32.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.32.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.32.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.33.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.33.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.33.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.34.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.34.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.34.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.35.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.35.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.35.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.36.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.36.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.36.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.37.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.37.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.37.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.38.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.38.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.38.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.39.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.39.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.39.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.4.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.4.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.4.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.40.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.40.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.40.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.41.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.41.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.41.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.42.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.42.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.42.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.43.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.43.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.43.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.44.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.44.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.44.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.45.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.45.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.45.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.46.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.46.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.46.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.47.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.47.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.47.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.48.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.48.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.48.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.49.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.49.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.49.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.5.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.5.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.5.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.50.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.50.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.50.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.51.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.51.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.51.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.52.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.52.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.52.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.53.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.53.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.53.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.54.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.54.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.54.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.55.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.55.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.55.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.56.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.56.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.56.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.57.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.57.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.57.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.58.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.58.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.58.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.59.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.59.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.59.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.6.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.6.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.6.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.60.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.60.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.60.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.61.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.61.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.61.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.62.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.62.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.62.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.63.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.63.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.63.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.64.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.64.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.64.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.65.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.65.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.65.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.66.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.66.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.66.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.67.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.67.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.67.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.68.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.68.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.68.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.69.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.69.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.69.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.7.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.7.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.7.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.70.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.70.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.70.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.71.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.71.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.71.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.72.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.72.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.72.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.73.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.73.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.73.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.74.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.74.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.74.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.75.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.75.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.75.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.76.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.76.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.76.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.77.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.77.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.77.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.78.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.78.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.78.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.79.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.79.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.79.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.8.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.8.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.8.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.80.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.80.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.80.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.81.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.81.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.81.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.82.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.82.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.82.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.83.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.83.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.83.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.84.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.84.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.84.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.85.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.85.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.85.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.86.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.86.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.86.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.87.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.87.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.87.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.88.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.88.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.88.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.89.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.89.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.89.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.9.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.9.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.9.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.90.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.90.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.90.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.91.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.91.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.91.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.92.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.92.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.92.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.93.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.93.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.93.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.94.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.94.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.94.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.95.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.95.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.95.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.96.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.96.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.96.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.97.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.97.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.97.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.98.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.98.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.98.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.99.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.99.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.experts.99.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.gate.e_score_correction_bias": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.gate.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.shared_experts.down_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.shared_experts.gate_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.mlp.shared_experts.up_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00028-of-00092.safetensors", + "model.layers.27.self_attn.k_norm.weight": "model-00028-of-00092.safetensors", + "model.layers.27.self_attn.k_proj.bias": "model-00028-of-00092.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.self_attn.q_norm.weight": "model-00028-of-00092.safetensors", + "model.layers.27.self_attn.q_proj.bias": "model-00028-of-00092.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.27.self_attn.v_proj.bias": "model-00028-of-00092.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00028-of-00092.safetensors", + "model.layers.28.input_layernorm.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.0.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.0.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.0.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.1.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.1.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.1.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.10.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.10.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.10.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.100.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.100.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.100.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.101.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.101.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.101.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.102.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.102.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.102.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.103.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.103.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.103.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.104.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.104.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.104.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.105.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.105.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.105.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.106.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.106.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.106.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.107.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.107.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.107.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.108.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.108.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.108.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.109.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.109.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.109.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.11.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.11.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.11.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.110.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.110.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.110.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.111.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.111.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.111.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.112.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.112.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.112.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.113.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.113.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.113.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.114.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.114.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.114.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.115.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.115.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.115.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.116.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.116.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.116.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.117.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.117.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.117.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.118.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.118.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.118.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.119.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.119.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.119.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.12.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.12.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.12.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.120.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.120.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.120.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.121.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.121.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.121.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.122.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.122.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.122.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.123.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.123.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.123.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.124.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.124.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.124.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.125.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.125.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.125.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.126.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.126.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.126.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.127.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.127.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.127.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.128.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.128.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.128.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.129.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.129.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.129.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.13.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.13.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.13.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.130.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.130.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.130.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.131.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.131.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.131.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.132.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.132.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.132.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.133.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.133.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.133.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.134.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.134.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.134.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.135.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.135.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.135.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.136.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.136.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.136.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.137.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.137.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.137.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.138.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.138.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.138.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.139.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.139.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.139.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.14.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.14.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.14.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.140.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.140.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.140.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.141.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.141.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.141.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.142.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.142.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.142.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.143.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.143.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.143.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.144.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.144.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.144.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.145.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.145.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.145.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.146.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.146.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.146.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.147.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.147.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.147.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.148.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.148.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.148.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.149.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.149.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.149.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.15.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.15.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.15.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.150.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.150.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.150.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.151.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.151.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.151.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.152.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.152.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.152.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.153.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.153.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.153.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.154.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.154.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.154.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.155.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.155.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.155.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.156.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.156.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.156.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.157.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.157.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.157.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.158.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.158.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.158.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.159.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.159.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.159.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.16.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.16.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.16.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.17.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.17.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.17.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.18.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.18.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.18.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.19.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.19.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.19.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.2.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.2.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.2.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.20.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.20.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.20.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.21.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.21.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.21.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.22.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.22.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.22.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.23.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.23.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.23.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.24.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.24.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.24.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.25.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.25.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.25.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.26.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.26.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.26.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.27.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.27.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.27.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.28.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.28.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.28.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.29.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.29.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.29.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.3.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.3.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.3.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.30.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.30.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.30.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.31.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.31.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.31.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.32.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.32.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.32.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.33.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.33.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.33.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.34.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.34.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.34.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.35.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.35.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.35.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.36.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.36.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.36.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.37.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.37.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.37.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.38.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.38.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.38.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.39.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.39.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.39.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.4.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.4.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.4.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.40.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.40.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.40.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.41.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.41.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.41.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.42.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.42.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.42.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.43.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.43.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.43.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.44.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.44.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.44.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.45.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.45.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.45.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.46.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.46.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.46.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.47.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.47.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.47.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.48.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.48.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.48.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.49.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.49.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.49.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.5.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.5.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.5.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.50.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.50.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.50.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.51.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.51.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.51.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.52.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.52.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.52.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.53.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.53.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.53.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.54.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.54.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.54.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.55.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.55.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.55.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.56.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.56.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.56.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.57.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.57.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.57.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.58.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.58.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.58.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.59.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.59.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.59.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.6.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.6.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.6.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.60.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.60.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.60.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.61.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.61.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.61.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.62.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.62.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.62.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.63.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.63.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.63.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.64.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.64.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.64.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.65.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.65.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.65.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.66.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.66.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.66.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.67.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.67.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.67.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.68.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.68.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.68.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.69.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.69.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.69.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.7.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.7.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.7.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.70.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.70.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.70.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.71.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.71.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.71.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.72.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.72.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.72.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.73.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.73.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.73.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.74.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.74.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.74.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.75.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.75.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.75.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.76.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.76.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.76.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.77.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.77.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.77.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.78.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.78.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.78.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.79.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.79.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.79.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.8.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.8.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.8.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.80.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.80.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.80.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.81.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.81.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.81.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.82.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.82.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.82.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.83.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.83.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.83.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.84.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.84.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.84.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.85.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.85.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.85.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.86.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.86.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.86.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.87.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.87.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.87.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.88.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.88.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.88.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.89.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.89.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.89.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.9.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.9.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.9.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.90.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.90.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.90.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.91.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.91.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.91.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.92.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.92.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.92.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.93.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.93.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.93.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.94.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.94.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.94.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.95.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.95.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.95.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.96.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.96.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.96.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.97.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.97.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.97.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.98.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.98.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.98.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.99.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.99.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.experts.99.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.gate.e_score_correction_bias": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.gate.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.shared_experts.down_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.shared_experts.gate_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.mlp.shared_experts.up_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00029-of-00092.safetensors", + "model.layers.28.self_attn.k_norm.weight": "model-00029-of-00092.safetensors", + "model.layers.28.self_attn.k_proj.bias": "model-00029-of-00092.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.self_attn.q_norm.weight": "model-00029-of-00092.safetensors", + "model.layers.28.self_attn.q_proj.bias": "model-00029-of-00092.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.28.self_attn.v_proj.bias": "model-00029-of-00092.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00029-of-00092.safetensors", + "model.layers.29.input_layernorm.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.0.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.0.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.0.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.1.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.1.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.1.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.10.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.10.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.10.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.100.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.100.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.100.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.101.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.101.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.101.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.102.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.102.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.102.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.103.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.103.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.103.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.104.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.104.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.104.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.105.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.105.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.105.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.106.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.106.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.106.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.107.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.107.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.107.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.108.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.108.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.108.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.109.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.109.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.109.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.11.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.11.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.11.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.110.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.110.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.110.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.111.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.111.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.111.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.112.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.112.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.112.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.113.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.113.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.113.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.114.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.114.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.114.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.115.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.115.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.115.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.116.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.116.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.116.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.117.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.117.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.117.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.118.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.118.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.118.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.119.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.119.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.119.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.12.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.12.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.12.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.120.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.120.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.120.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.121.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.121.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.121.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.122.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.122.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.122.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.123.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.123.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.123.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.124.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.124.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.124.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.125.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.125.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.125.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.126.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.126.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.126.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.127.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.127.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.127.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.128.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.128.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.128.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.129.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.129.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.129.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.13.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.13.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.13.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.130.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.130.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.130.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.131.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.131.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.131.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.132.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.132.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.132.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.133.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.133.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.133.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.134.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.134.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.134.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.135.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.135.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.135.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.136.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.136.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.136.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.137.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.137.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.137.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.138.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.138.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.138.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.139.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.139.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.139.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.14.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.14.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.14.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.140.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.140.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.140.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.141.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.141.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.141.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.142.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.142.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.142.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.143.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.143.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.143.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.144.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.144.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.144.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.145.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.145.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.145.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.146.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.146.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.146.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.147.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.147.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.147.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.148.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.148.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.148.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.149.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.149.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.149.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.15.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.15.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.15.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.150.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.150.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.150.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.151.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.151.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.151.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.152.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.152.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.152.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.153.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.153.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.153.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.154.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.154.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.154.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.155.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.155.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.155.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.156.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.156.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.156.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.157.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.157.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.157.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.158.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.158.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.158.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.159.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.159.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.159.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.16.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.16.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.16.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.17.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.17.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.17.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.18.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.18.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.18.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.19.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.19.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.19.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.2.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.2.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.2.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.20.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.20.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.20.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.21.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.21.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.21.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.22.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.22.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.22.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.23.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.23.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.23.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.24.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.24.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.24.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.25.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.25.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.25.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.26.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.26.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.26.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.27.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.27.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.27.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.28.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.28.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.28.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.29.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.29.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.29.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.3.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.3.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.3.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.30.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.30.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.30.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.31.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.31.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.31.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.32.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.32.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.32.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.33.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.33.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.33.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.34.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.34.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.34.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.35.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.35.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.35.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.36.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.36.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.36.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.37.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.37.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.37.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.38.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.38.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.38.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.39.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.39.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.39.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.4.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.4.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.4.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.40.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.40.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.40.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.41.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.41.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.41.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.42.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.42.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.42.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.43.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.43.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.43.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.44.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.44.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.44.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.45.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.45.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.45.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.46.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.46.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.46.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.47.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.47.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.47.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.48.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.48.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.48.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.49.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.49.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.49.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.5.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.5.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.5.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.50.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.50.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.50.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.51.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.51.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.51.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.52.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.52.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.52.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.53.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.53.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.53.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.54.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.54.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.54.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.55.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.55.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.55.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.56.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.56.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.56.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.57.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.57.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.57.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.58.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.58.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.58.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.59.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.59.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.59.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.6.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.6.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.6.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.60.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.60.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.60.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.61.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.61.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.61.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.62.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.62.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.62.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.63.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.63.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.63.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.64.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.64.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.64.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.65.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.65.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.65.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.66.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.66.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.66.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.67.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.67.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.67.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.68.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.68.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.68.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.69.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.69.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.69.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.7.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.7.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.7.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.70.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.70.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.70.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.71.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.71.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.71.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.72.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.72.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.72.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.73.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.73.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.73.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.74.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.74.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.74.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.75.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.75.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.75.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.76.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.76.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.76.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.77.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.77.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.77.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.78.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.78.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.78.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.79.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.79.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.79.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.8.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.8.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.8.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.80.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.80.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.80.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.81.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.81.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.81.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.82.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.82.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.82.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.83.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.83.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.83.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.84.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.84.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.84.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.85.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.85.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.85.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.86.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.86.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.86.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.87.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.87.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.87.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.88.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.88.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.88.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.89.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.89.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.89.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.9.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.9.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.9.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.90.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.90.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.90.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.91.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.91.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.91.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.92.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.92.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.92.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.93.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.93.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.93.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.94.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.94.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.94.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.95.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.95.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.95.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.96.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.96.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.96.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.97.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.97.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.97.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.98.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.98.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.98.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.99.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.99.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.experts.99.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.gate.e_score_correction_bias": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.gate.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.shared_experts.down_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.shared_experts.gate_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.mlp.shared_experts.up_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00030-of-00092.safetensors", + "model.layers.29.self_attn.k_norm.weight": "model-00030-of-00092.safetensors", + "model.layers.29.self_attn.k_proj.bias": "model-00030-of-00092.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.self_attn.q_norm.weight": "model-00030-of-00092.safetensors", + "model.layers.29.self_attn.q_proj.bias": "model-00030-of-00092.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.29.self_attn.v_proj.bias": "model-00030-of-00092.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00030-of-00092.safetensors", + "model.layers.30.input_layernorm.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.0.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.0.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.0.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.1.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.1.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.1.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.10.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.10.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.10.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.100.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.100.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.100.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.101.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.101.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.101.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.102.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.102.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.102.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.103.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.103.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.103.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.104.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.104.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.104.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.105.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.105.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.105.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.106.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.106.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.106.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.107.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.107.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.107.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.108.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.108.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.108.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.109.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.109.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.109.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.11.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.11.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.11.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.110.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.110.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.110.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.111.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.111.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.111.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.112.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.112.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.112.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.113.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.113.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.113.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.114.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.114.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.114.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.115.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.115.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.115.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.116.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.116.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.116.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.117.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.117.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.117.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.118.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.118.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.118.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.119.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.119.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.119.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.12.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.12.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.12.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.120.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.120.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.120.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.121.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.121.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.121.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.122.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.122.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.122.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.123.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.123.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.123.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.124.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.124.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.124.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.125.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.125.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.125.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.126.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.126.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.126.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.127.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.127.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.127.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.128.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.128.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.128.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.129.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.129.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.129.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.13.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.13.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.13.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.130.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.130.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.130.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.131.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.131.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.131.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.132.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.132.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.132.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.133.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.133.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.133.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.134.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.134.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.134.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.135.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.135.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.135.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.136.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.136.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.136.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.137.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.137.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.137.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.138.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.138.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.138.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.139.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.139.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.139.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.14.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.14.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.14.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.140.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.140.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.140.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.141.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.141.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.141.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.142.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.142.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.142.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.143.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.143.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.143.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.144.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.144.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.144.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.145.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.145.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.145.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.146.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.146.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.146.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.147.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.147.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.147.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.148.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.148.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.148.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.149.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.149.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.149.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.15.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.15.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.15.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.150.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.150.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.150.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.151.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.151.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.151.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.152.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.152.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.152.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.153.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.153.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.153.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.154.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.154.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.154.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.155.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.155.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.155.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.156.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.156.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.156.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.157.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.157.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.157.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.158.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.158.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.158.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.159.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.159.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.159.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.16.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.16.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.16.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.17.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.17.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.17.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.18.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.18.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.18.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.19.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.19.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.19.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.2.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.2.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.2.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.20.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.20.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.20.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.21.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.21.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.21.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.22.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.22.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.22.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.23.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.23.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.23.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.24.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.24.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.24.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.25.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.25.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.25.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.26.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.26.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.26.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.27.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.27.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.27.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.28.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.28.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.28.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.29.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.29.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.29.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.3.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.3.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.3.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.30.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.30.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.30.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.31.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.31.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.31.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.32.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.32.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.32.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.33.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.33.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.33.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.34.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.34.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.34.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.35.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.35.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.35.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.36.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.36.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.36.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.37.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.37.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.37.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.38.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.38.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.38.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.39.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.39.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.39.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.4.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.4.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.4.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.40.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.40.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.40.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.41.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.41.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.41.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.42.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.42.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.42.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.43.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.43.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.43.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.44.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.44.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.44.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.45.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.45.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.45.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.46.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.46.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.46.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.47.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.47.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.47.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.48.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.48.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.48.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.49.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.49.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.49.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.5.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.5.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.5.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.50.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.50.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.50.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.51.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.51.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.51.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.52.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.52.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.52.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.53.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.53.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.53.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.54.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.54.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.54.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.55.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.55.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.55.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.56.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.56.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.56.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.57.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.57.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.57.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.58.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.58.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.58.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.59.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.59.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.59.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.6.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.6.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.6.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.60.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.60.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.60.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.61.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.61.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.61.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.62.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.62.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.62.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.63.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.63.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.63.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.64.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.64.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.64.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.65.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.65.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.65.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.66.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.66.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.66.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.67.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.67.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.67.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.68.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.68.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.68.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.69.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.69.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.69.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.7.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.7.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.7.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.70.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.70.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.70.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.71.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.71.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.71.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.72.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.72.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.72.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.73.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.73.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.73.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.74.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.74.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.74.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.75.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.75.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.75.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.76.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.76.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.76.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.77.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.77.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.77.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.78.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.78.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.78.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.79.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.79.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.79.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.8.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.8.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.8.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.80.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.80.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.80.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.81.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.81.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.81.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.82.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.82.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.82.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.83.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.83.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.83.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.84.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.84.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.84.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.85.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.85.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.85.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.86.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.86.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.86.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.87.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.87.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.87.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.88.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.88.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.88.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.89.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.89.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.89.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.9.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.9.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.9.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.90.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.90.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.90.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.91.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.91.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.91.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.92.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.92.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.92.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.93.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.93.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.93.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.94.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.94.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.94.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.95.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.95.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.95.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.96.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.96.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.96.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.97.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.97.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.97.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.98.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.98.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.98.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.99.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.99.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.experts.99.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.gate.e_score_correction_bias": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.gate.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.shared_experts.down_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.shared_experts.gate_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.mlp.shared_experts.up_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00031-of-00092.safetensors", + "model.layers.30.self_attn.k_norm.weight": "model-00031-of-00092.safetensors", + "model.layers.30.self_attn.k_proj.bias": "model-00031-of-00092.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.self_attn.q_norm.weight": "model-00031-of-00092.safetensors", + "model.layers.30.self_attn.q_proj.bias": "model-00031-of-00092.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.30.self_attn.v_proj.bias": "model-00031-of-00092.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00031-of-00092.safetensors", + "model.layers.31.input_layernorm.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.0.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.0.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.0.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.1.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.1.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.1.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.10.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.10.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.10.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.100.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.100.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.100.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.101.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.101.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.101.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.102.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.102.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.102.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.103.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.103.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.103.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.104.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.104.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.104.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.105.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.105.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.105.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.106.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.106.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.106.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.107.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.107.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.107.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.108.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.108.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.108.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.109.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.109.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.109.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.11.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.11.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.11.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.110.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.110.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.110.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.111.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.111.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.111.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.112.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.112.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.112.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.113.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.113.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.113.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.114.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.114.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.114.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.115.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.115.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.115.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.116.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.116.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.116.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.117.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.117.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.117.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.118.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.118.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.118.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.119.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.119.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.119.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.12.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.12.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.12.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.120.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.120.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.120.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.121.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.121.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.121.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.122.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.122.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.122.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.123.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.123.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.123.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.124.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.124.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.124.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.125.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.125.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.125.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.126.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.126.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.126.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.127.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.127.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.127.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.128.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.128.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.128.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.129.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.129.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.129.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.13.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.13.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.13.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.130.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.130.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.130.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.131.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.131.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.131.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.132.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.132.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.132.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.133.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.133.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.133.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.134.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.134.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.134.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.135.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.135.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.135.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.136.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.136.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.136.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.137.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.137.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.137.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.138.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.138.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.138.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.139.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.139.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.139.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.14.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.14.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.14.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.140.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.140.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.140.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.141.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.141.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.141.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.142.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.142.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.142.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.143.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.143.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.143.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.144.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.144.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.144.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.145.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.145.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.145.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.146.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.146.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.146.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.147.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.147.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.147.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.148.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.148.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.148.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.149.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.149.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.149.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.15.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.15.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.15.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.150.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.150.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.150.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.151.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.151.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.151.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.152.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.152.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.152.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.153.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.153.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.153.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.154.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.154.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.154.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.155.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.155.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.155.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.156.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.156.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.156.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.157.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.157.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.157.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.158.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.158.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.158.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.159.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.159.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.159.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.16.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.16.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.16.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.17.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.17.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.17.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.18.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.18.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.18.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.19.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.19.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.19.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.2.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.2.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.2.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.20.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.20.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.20.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.21.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.21.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.21.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.22.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.22.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.22.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.23.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.23.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.23.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.24.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.24.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.24.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.25.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.25.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.25.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.26.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.26.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.26.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.27.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.27.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.27.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.28.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.28.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.28.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.29.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.29.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.29.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.3.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.3.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.3.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.30.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.30.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.30.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.31.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.31.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.31.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.32.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.32.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.32.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.33.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.33.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.33.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.34.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.34.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.34.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.35.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.35.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.35.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.36.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.36.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.36.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.37.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.37.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.37.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.38.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.38.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.38.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.39.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.39.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.39.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.4.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.4.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.4.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.40.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.40.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.40.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.41.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.41.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.41.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.42.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.42.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.42.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.43.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.43.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.43.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.44.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.44.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.44.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.45.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.45.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.45.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.46.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.46.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.46.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.47.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.47.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.47.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.48.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.48.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.48.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.49.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.49.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.49.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.5.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.5.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.5.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.50.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.50.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.50.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.51.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.51.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.51.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.52.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.52.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.52.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.53.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.53.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.53.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.54.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.54.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.54.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.55.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.55.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.55.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.56.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.56.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.56.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.57.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.57.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.57.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.58.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.58.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.58.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.59.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.59.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.59.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.6.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.6.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.6.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.60.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.60.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.60.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.61.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.61.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.61.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.62.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.62.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.62.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.63.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.63.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.63.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.64.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.64.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.64.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.65.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.65.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.65.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.66.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.66.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.66.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.67.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.67.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.67.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.68.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.68.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.68.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.69.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.69.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.69.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.7.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.7.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.7.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.70.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.70.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.70.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.71.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.71.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.71.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.72.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.72.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.72.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.73.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.73.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.73.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.74.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.74.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.74.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.75.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.75.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.75.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.76.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.76.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.76.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.77.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.77.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.77.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.78.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.78.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.78.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.79.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.79.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.79.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.8.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.8.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.8.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.80.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.80.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.80.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.81.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.81.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.81.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.82.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.82.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.82.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.83.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.83.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.83.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.84.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.84.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.84.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.85.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.85.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.85.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.86.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.86.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.86.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.87.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.87.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.87.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.88.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.88.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.88.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.89.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.89.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.89.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.9.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.9.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.9.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.90.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.90.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.90.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.91.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.91.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.91.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.92.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.92.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.92.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.93.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.93.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.93.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.94.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.94.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.94.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.95.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.95.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.95.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.96.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.96.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.96.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.97.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.97.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.97.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.98.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.98.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.98.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.99.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.99.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.experts.99.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.gate.e_score_correction_bias": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.gate.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.shared_experts.down_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.shared_experts.gate_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.mlp.shared_experts.up_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00032-of-00092.safetensors", + "model.layers.31.self_attn.k_norm.weight": "model-00032-of-00092.safetensors", + "model.layers.31.self_attn.k_proj.bias": "model-00032-of-00092.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.self_attn.q_norm.weight": "model-00032-of-00092.safetensors", + "model.layers.31.self_attn.q_proj.bias": "model-00032-of-00092.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.31.self_attn.v_proj.bias": "model-00032-of-00092.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00032-of-00092.safetensors", + "model.layers.32.input_layernorm.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.0.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.0.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.0.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.1.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.1.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.1.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.10.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.10.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.10.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.100.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.100.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.100.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.101.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.101.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.101.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.102.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.102.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.102.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.103.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.103.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.103.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.104.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.104.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.104.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.105.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.105.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.105.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.106.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.106.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.106.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.107.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.107.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.107.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.108.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.108.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.108.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.109.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.109.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.109.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.11.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.11.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.11.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.110.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.110.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.110.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.111.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.111.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.111.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.112.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.112.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.112.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.113.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.113.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.113.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.114.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.114.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.114.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.115.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.115.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.115.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.116.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.116.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.116.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.117.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.117.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.117.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.118.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.118.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.118.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.119.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.119.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.119.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.12.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.12.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.12.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.120.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.120.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.120.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.121.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.121.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.121.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.122.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.122.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.122.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.123.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.123.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.123.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.124.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.124.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.124.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.125.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.125.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.125.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.126.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.126.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.126.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.127.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.127.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.127.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.128.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.128.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.128.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.129.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.129.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.129.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.13.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.13.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.13.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.130.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.130.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.130.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.131.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.131.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.131.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.132.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.132.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.132.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.133.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.133.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.133.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.134.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.134.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.134.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.135.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.135.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.135.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.136.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.136.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.136.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.137.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.137.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.137.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.138.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.138.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.138.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.139.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.139.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.139.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.14.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.14.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.14.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.140.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.140.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.140.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.141.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.141.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.141.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.142.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.142.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.142.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.143.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.143.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.143.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.144.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.144.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.144.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.145.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.145.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.145.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.146.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.146.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.146.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.147.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.147.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.147.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.148.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.148.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.148.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.149.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.149.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.149.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.15.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.15.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.15.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.150.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.150.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.150.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.151.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.151.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.151.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.152.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.152.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.152.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.153.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.153.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.153.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.154.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.154.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.154.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.155.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.155.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.155.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.156.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.156.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.156.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.157.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.157.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.157.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.158.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.158.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.158.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.159.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.159.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.159.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.16.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.16.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.16.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.17.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.17.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.17.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.18.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.18.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.18.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.19.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.19.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.19.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.2.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.2.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.2.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.20.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.20.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.20.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.21.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.21.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.21.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.22.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.22.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.22.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.23.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.23.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.23.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.24.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.24.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.24.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.25.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.25.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.25.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.26.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.26.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.26.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.27.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.27.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.27.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.28.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.28.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.28.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.29.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.29.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.29.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.3.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.3.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.3.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.30.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.30.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.30.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.31.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.31.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.31.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.32.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.32.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.32.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.33.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.33.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.33.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.34.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.34.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.34.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.35.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.35.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.35.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.36.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.36.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.36.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.37.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.37.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.37.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.38.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.38.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.38.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.39.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.39.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.39.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.4.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.4.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.4.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.40.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.40.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.40.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.41.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.41.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.41.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.42.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.42.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.42.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.43.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.43.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.43.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.44.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.44.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.44.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.45.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.45.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.45.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.46.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.46.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.46.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.47.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.47.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.47.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.48.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.48.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.48.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.49.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.49.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.49.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.5.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.5.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.5.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.50.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.50.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.50.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.51.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.51.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.51.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.52.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.52.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.52.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.53.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.53.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.53.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.54.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.54.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.54.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.55.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.55.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.55.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.56.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.56.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.56.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.57.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.57.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.57.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.58.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.58.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.58.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.59.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.59.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.59.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.6.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.6.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.6.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.60.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.60.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.60.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.61.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.61.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.61.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.62.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.62.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.62.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.63.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.63.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.63.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.64.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.64.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.64.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.65.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.65.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.65.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.66.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.66.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.66.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.67.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.67.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.67.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.68.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.68.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.68.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.69.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.69.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.69.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.7.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.7.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.7.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.70.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.70.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.70.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.71.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.71.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.71.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.72.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.72.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.72.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.73.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.73.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.73.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.74.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.74.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.74.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.75.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.75.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.75.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.76.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.76.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.76.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.77.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.77.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.77.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.78.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.78.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.78.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.79.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.79.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.79.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.8.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.8.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.8.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.80.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.80.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.80.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.81.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.81.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.81.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.82.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.82.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.82.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.83.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.83.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.83.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.84.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.84.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.84.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.85.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.85.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.85.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.86.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.86.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.86.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.87.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.87.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.87.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.88.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.88.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.88.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.89.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.89.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.89.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.9.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.9.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.9.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.90.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.90.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.90.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.91.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.91.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.91.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.92.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.92.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.92.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.93.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.93.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.93.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.94.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.94.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.94.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.95.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.95.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.95.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.96.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.96.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.96.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.97.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.97.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.97.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.98.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.98.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.98.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.99.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.99.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.experts.99.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.gate.e_score_correction_bias": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.gate.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.shared_experts.down_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.shared_experts.gate_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.mlp.shared_experts.up_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.post_attention_layernorm.weight": "model-00033-of-00092.safetensors", + "model.layers.32.self_attn.k_norm.weight": "model-00033-of-00092.safetensors", + "model.layers.32.self_attn.k_proj.bias": "model-00033-of-00092.safetensors", + "model.layers.32.self_attn.k_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.self_attn.o_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.self_attn.q_norm.weight": "model-00033-of-00092.safetensors", + "model.layers.32.self_attn.q_proj.bias": "model-00033-of-00092.safetensors", + "model.layers.32.self_attn.q_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.32.self_attn.v_proj.bias": "model-00033-of-00092.safetensors", + "model.layers.32.self_attn.v_proj.weight": "model-00033-of-00092.safetensors", + "model.layers.33.input_layernorm.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.0.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.0.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.0.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.1.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.1.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.1.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.10.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.10.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.10.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.100.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.100.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.100.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.101.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.101.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.101.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.102.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.102.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.102.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.103.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.103.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.103.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.104.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.104.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.104.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.105.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.105.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.105.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.106.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.106.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.106.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.107.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.107.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.107.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.108.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.108.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.108.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.109.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.109.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.109.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.11.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.11.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.11.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.110.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.110.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.110.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.111.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.111.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.111.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.112.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.112.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.112.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.113.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.113.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.113.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.114.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.114.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.114.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.115.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.115.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.115.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.116.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.116.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.116.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.117.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.117.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.117.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.118.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.118.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.118.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.119.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.119.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.119.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.12.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.12.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.12.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.120.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.120.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.120.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.121.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.121.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.121.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.122.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.122.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.122.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.123.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.123.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.123.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.124.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.124.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.124.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.125.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.125.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.125.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.126.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.126.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.126.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.127.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.127.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.127.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.128.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.128.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.128.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.129.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.129.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.129.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.13.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.13.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.13.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.130.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.130.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.130.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.131.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.131.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.131.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.132.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.132.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.132.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.133.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.133.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.133.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.134.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.134.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.134.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.135.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.135.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.135.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.136.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.136.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.136.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.137.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.137.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.137.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.138.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.138.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.138.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.139.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.139.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.139.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.14.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.14.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.14.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.140.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.140.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.140.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.141.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.141.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.141.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.142.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.142.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.142.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.143.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.143.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.143.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.144.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.144.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.144.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.145.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.145.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.145.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.146.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.146.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.146.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.147.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.147.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.147.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.148.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.148.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.148.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.149.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.149.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.149.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.15.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.15.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.15.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.150.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.150.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.150.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.151.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.151.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.151.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.152.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.152.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.152.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.153.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.153.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.153.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.154.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.154.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.154.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.155.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.155.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.155.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.156.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.156.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.156.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.157.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.157.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.157.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.158.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.158.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.158.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.159.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.159.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.159.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.16.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.16.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.16.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.17.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.17.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.17.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.18.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.18.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.18.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.19.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.19.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.19.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.2.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.2.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.2.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.20.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.20.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.20.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.21.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.21.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.21.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.22.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.22.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.22.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.23.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.23.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.23.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.24.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.24.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.24.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.25.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.25.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.25.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.26.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.26.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.26.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.27.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.27.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.27.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.28.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.28.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.28.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.29.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.29.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.29.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.3.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.3.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.3.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.30.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.30.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.30.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.31.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.31.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.31.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.32.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.32.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.32.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.33.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.33.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.33.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.34.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.34.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.34.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.35.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.35.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.35.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.36.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.36.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.36.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.37.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.37.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.37.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.38.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.38.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.38.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.39.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.39.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.39.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.4.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.4.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.4.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.40.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.40.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.40.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.41.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.41.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.41.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.42.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.42.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.42.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.43.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.43.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.43.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.44.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.44.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.44.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.45.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.45.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.45.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.46.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.46.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.46.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.47.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.47.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.47.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.48.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.48.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.48.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.49.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.49.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.49.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.5.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.5.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.5.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.50.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.50.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.50.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.51.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.51.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.51.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.52.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.52.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.52.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.53.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.53.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.53.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.54.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.54.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.54.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.55.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.55.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.55.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.56.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.56.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.56.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.57.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.57.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.57.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.58.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.58.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.58.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.59.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.59.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.59.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.6.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.6.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.6.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.60.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.60.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.60.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.61.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.61.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.61.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.62.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.62.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.62.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.63.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.63.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.63.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.64.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.64.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.64.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.65.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.65.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.65.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.66.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.66.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.66.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.67.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.67.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.67.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.68.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.68.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.68.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.69.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.69.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.69.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.7.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.7.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.7.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.70.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.70.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.70.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.71.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.71.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.71.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.72.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.72.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.72.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.73.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.73.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.73.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.74.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.74.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.74.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.75.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.75.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.75.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.76.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.76.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.76.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.77.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.77.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.77.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.78.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.78.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.78.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.79.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.79.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.79.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.8.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.8.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.8.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.80.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.80.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.80.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.81.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.81.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.81.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.82.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.82.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.82.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.83.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.83.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.83.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.84.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.84.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.84.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.85.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.85.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.85.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.86.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.86.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.86.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.87.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.87.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.87.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.88.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.88.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.88.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.89.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.89.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.89.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.9.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.9.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.9.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.90.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.90.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.90.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.91.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.91.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.91.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.92.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.92.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.92.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.93.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.93.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.93.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.94.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.94.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.94.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.95.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.95.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.95.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.96.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.96.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.96.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.97.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.97.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.97.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.98.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.98.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.98.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.99.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.99.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.experts.99.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.gate.e_score_correction_bias": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.gate.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.shared_experts.down_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.shared_experts.gate_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.mlp.shared_experts.up_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.post_attention_layernorm.weight": "model-00034-of-00092.safetensors", + "model.layers.33.self_attn.k_norm.weight": "model-00034-of-00092.safetensors", + "model.layers.33.self_attn.k_proj.bias": "model-00034-of-00092.safetensors", + "model.layers.33.self_attn.k_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.self_attn.o_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.self_attn.q_norm.weight": "model-00034-of-00092.safetensors", + "model.layers.33.self_attn.q_proj.bias": "model-00034-of-00092.safetensors", + "model.layers.33.self_attn.q_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.33.self_attn.v_proj.bias": "model-00034-of-00092.safetensors", + "model.layers.33.self_attn.v_proj.weight": "model-00034-of-00092.safetensors", + "model.layers.34.input_layernorm.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.0.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.0.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.0.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.1.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.1.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.1.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.10.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.10.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.10.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.100.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.100.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.100.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.101.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.101.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.101.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.102.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.102.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.102.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.103.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.103.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.103.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.104.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.104.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.104.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.105.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.105.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.105.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.106.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.106.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.106.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.107.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.107.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.107.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.108.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.108.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.108.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.109.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.109.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.109.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.11.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.11.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.11.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.110.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.110.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.110.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.111.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.111.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.111.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.112.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.112.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.112.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.113.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.113.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.113.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.114.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.114.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.114.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.115.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.115.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.115.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.116.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.116.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.116.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.117.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.117.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.117.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.118.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.118.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.118.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.119.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.119.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.119.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.12.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.12.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.12.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.120.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.120.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.120.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.121.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.121.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.121.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.122.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.122.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.122.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.123.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.123.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.123.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.124.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.124.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.124.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.125.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.125.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.125.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.126.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.126.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.126.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.127.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.127.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.127.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.128.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.128.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.128.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.129.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.129.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.129.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.13.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.13.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.13.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.130.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.130.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.130.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.131.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.131.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.131.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.132.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.132.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.132.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.133.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.133.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.133.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.134.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.134.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.134.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.135.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.135.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.135.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.136.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.136.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.136.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.137.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.137.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.137.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.138.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.138.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.138.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.139.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.139.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.139.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.14.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.14.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.14.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.140.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.140.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.140.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.141.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.141.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.141.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.142.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.142.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.142.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.143.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.143.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.143.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.144.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.144.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.144.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.145.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.145.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.145.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.146.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.146.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.146.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.147.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.147.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.147.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.148.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.148.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.148.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.149.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.149.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.149.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.15.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.15.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.15.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.150.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.150.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.150.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.151.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.151.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.151.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.152.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.152.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.152.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.153.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.153.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.153.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.154.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.154.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.154.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.155.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.155.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.155.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.156.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.156.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.156.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.157.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.157.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.157.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.158.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.158.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.158.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.159.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.159.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.159.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.16.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.16.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.16.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.17.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.17.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.17.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.18.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.18.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.18.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.19.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.19.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.19.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.2.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.2.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.2.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.20.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.20.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.20.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.21.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.21.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.21.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.22.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.22.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.22.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.23.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.23.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.23.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.24.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.24.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.24.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.25.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.25.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.25.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.26.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.26.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.26.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.27.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.27.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.27.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.28.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.28.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.28.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.29.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.29.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.29.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.3.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.3.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.3.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.30.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.30.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.30.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.31.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.31.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.31.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.32.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.32.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.32.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.33.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.33.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.33.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.34.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.34.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.34.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.35.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.35.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.35.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.36.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.36.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.36.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.37.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.37.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.37.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.38.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.38.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.38.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.39.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.39.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.39.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.4.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.4.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.4.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.40.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.40.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.40.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.41.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.41.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.41.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.42.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.42.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.42.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.43.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.43.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.43.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.44.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.44.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.44.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.45.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.45.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.45.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.46.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.46.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.46.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.47.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.47.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.47.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.48.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.48.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.48.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.49.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.49.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.49.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.5.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.5.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.5.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.50.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.50.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.50.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.51.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.51.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.51.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.52.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.52.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.52.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.53.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.53.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.53.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.54.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.54.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.54.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.55.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.55.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.55.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.56.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.56.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.56.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.57.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.57.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.57.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.58.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.58.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.58.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.59.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.59.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.59.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.6.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.6.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.6.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.60.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.60.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.60.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.61.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.61.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.61.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.62.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.62.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.62.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.63.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.63.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.63.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.64.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.64.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.64.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.65.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.65.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.65.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.66.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.66.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.66.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.67.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.67.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.67.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.68.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.68.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.68.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.69.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.69.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.69.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.7.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.7.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.7.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.70.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.70.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.70.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.71.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.71.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.71.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.72.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.72.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.72.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.73.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.73.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.73.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.74.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.74.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.74.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.75.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.75.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.75.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.76.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.76.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.76.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.77.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.77.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.77.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.78.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.78.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.78.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.79.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.79.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.79.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.8.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.8.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.8.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.80.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.80.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.80.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.81.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.81.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.81.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.82.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.82.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.82.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.83.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.83.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.83.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.84.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.84.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.84.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.85.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.85.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.85.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.86.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.86.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.86.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.87.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.87.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.87.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.88.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.88.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.88.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.89.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.89.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.89.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.9.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.9.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.9.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.90.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.90.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.90.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.91.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.91.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.91.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.92.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.92.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.92.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.93.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.93.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.93.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.94.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.94.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.94.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.95.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.95.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.95.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.96.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.96.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.96.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.97.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.97.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.97.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.98.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.98.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.98.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.99.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.99.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.experts.99.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.gate.e_score_correction_bias": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.gate.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.shared_experts.down_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.shared_experts.gate_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.mlp.shared_experts.up_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.post_attention_layernorm.weight": "model-00035-of-00092.safetensors", + "model.layers.34.self_attn.k_norm.weight": "model-00035-of-00092.safetensors", + "model.layers.34.self_attn.k_proj.bias": "model-00035-of-00092.safetensors", + "model.layers.34.self_attn.k_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.self_attn.o_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.self_attn.q_norm.weight": "model-00035-of-00092.safetensors", + "model.layers.34.self_attn.q_proj.bias": "model-00035-of-00092.safetensors", + "model.layers.34.self_attn.q_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.34.self_attn.v_proj.bias": "model-00035-of-00092.safetensors", + "model.layers.34.self_attn.v_proj.weight": "model-00035-of-00092.safetensors", + "model.layers.35.input_layernorm.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.0.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.0.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.0.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.1.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.1.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.1.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.10.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.10.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.10.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.100.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.100.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.100.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.101.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.101.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.101.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.102.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.102.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.102.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.103.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.103.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.103.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.104.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.104.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.104.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.105.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.105.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.105.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.106.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.106.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.106.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.107.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.107.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.107.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.108.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.108.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.108.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.109.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.109.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.109.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.11.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.11.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.11.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.110.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.110.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.110.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.111.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.111.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.111.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.112.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.112.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.112.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.113.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.113.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.113.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.114.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.114.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.114.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.115.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.115.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.115.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.116.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.116.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.116.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.117.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.117.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.117.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.118.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.118.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.118.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.119.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.119.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.119.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.12.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.12.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.12.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.120.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.120.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.120.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.121.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.121.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.121.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.122.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.122.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.122.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.123.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.123.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.123.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.124.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.124.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.124.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.125.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.125.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.125.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.126.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.126.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.126.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.127.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.127.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.127.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.128.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.128.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.128.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.129.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.129.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.129.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.13.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.13.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.13.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.130.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.130.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.130.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.131.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.131.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.131.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.132.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.132.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.132.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.133.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.133.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.133.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.134.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.134.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.134.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.135.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.135.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.135.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.136.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.136.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.136.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.137.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.137.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.137.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.138.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.138.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.138.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.139.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.139.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.139.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.14.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.14.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.14.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.140.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.140.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.140.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.141.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.141.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.141.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.142.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.142.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.142.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.143.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.143.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.143.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.144.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.144.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.144.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.145.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.145.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.145.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.146.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.146.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.146.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.147.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.147.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.147.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.148.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.148.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.148.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.149.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.149.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.149.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.15.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.15.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.15.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.150.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.150.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.150.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.151.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.151.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.151.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.152.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.152.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.152.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.153.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.153.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.153.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.154.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.154.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.154.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.155.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.155.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.155.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.156.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.156.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.156.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.157.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.157.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.157.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.158.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.158.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.158.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.159.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.159.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.159.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.16.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.16.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.16.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.17.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.17.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.17.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.18.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.18.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.18.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.19.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.19.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.19.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.2.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.2.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.2.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.20.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.20.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.20.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.21.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.21.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.21.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.22.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.22.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.22.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.23.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.23.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.23.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.24.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.24.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.24.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.25.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.25.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.25.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.26.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.26.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.26.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.27.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.27.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.27.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.28.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.28.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.28.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.29.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.29.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.29.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.3.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.3.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.3.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.30.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.30.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.30.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.31.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.31.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.31.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.32.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.32.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.32.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.33.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.33.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.33.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.34.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.34.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.34.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.35.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.35.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.35.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.36.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.36.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.36.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.37.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.37.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.37.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.38.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.38.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.38.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.39.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.39.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.39.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.4.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.4.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.4.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.40.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.40.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.40.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.41.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.41.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.41.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.42.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.42.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.42.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.43.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.43.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.43.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.44.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.44.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.44.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.45.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.45.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.45.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.46.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.46.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.46.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.47.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.47.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.47.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.48.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.48.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.48.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.49.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.49.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.49.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.5.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.5.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.5.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.50.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.50.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.50.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.51.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.51.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.51.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.52.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.52.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.52.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.53.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.53.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.53.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.54.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.54.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.54.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.55.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.55.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.55.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.56.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.56.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.56.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.57.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.57.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.57.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.58.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.58.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.58.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.59.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.59.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.59.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.6.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.6.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.6.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.60.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.60.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.60.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.61.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.61.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.61.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.62.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.62.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.62.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.63.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.63.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.63.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.64.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.64.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.64.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.65.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.65.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.65.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.66.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.66.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.66.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.67.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.67.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.67.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.68.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.68.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.68.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.69.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.69.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.69.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.7.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.7.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.7.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.70.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.70.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.70.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.71.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.71.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.71.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.72.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.72.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.72.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.73.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.73.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.73.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.74.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.74.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.74.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.75.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.75.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.75.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.76.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.76.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.76.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.77.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.77.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.77.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.78.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.78.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.78.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.79.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.79.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.79.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.8.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.8.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.8.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.80.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.80.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.80.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.81.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.81.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.81.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.82.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.82.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.82.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.83.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.83.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.83.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.84.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.84.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.84.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.85.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.85.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.85.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.86.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.86.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.86.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.87.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.87.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.87.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.88.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.88.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.88.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.89.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.89.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.89.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.9.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.9.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.9.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.90.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.90.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.90.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.91.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.91.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.91.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.92.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.92.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.92.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.93.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.93.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.93.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.94.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.94.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.94.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.95.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.95.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.95.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.96.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.96.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.96.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.97.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.97.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.97.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.98.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.98.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.98.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.99.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.99.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.experts.99.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.gate.e_score_correction_bias": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.gate.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.shared_experts.down_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.shared_experts.gate_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.mlp.shared_experts.up_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.post_attention_layernorm.weight": "model-00036-of-00092.safetensors", + "model.layers.35.self_attn.k_norm.weight": "model-00036-of-00092.safetensors", + "model.layers.35.self_attn.k_proj.bias": "model-00036-of-00092.safetensors", + "model.layers.35.self_attn.k_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.self_attn.o_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.self_attn.q_norm.weight": "model-00036-of-00092.safetensors", + "model.layers.35.self_attn.q_proj.bias": "model-00036-of-00092.safetensors", + "model.layers.35.self_attn.q_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.35.self_attn.v_proj.bias": "model-00036-of-00092.safetensors", + "model.layers.35.self_attn.v_proj.weight": "model-00036-of-00092.safetensors", + "model.layers.36.input_layernorm.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.0.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.0.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.0.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.1.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.1.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.1.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.10.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.10.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.10.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.100.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.100.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.100.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.101.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.101.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.101.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.102.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.102.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.102.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.103.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.103.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.103.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.104.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.104.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.104.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.105.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.105.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.105.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.106.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.106.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.106.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.107.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.107.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.107.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.108.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.108.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.108.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.109.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.109.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.109.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.11.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.11.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.11.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.110.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.110.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.110.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.111.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.111.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.111.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.112.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.112.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.112.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.113.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.113.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.113.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.114.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.114.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.114.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.115.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.115.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.115.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.116.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.116.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.116.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.117.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.117.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.117.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.118.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.118.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.118.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.119.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.119.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.119.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.12.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.12.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.12.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.120.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.120.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.120.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.121.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.121.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.121.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.122.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.122.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.122.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.123.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.123.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.123.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.124.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.124.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.124.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.125.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.125.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.125.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.126.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.126.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.126.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.127.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.127.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.127.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.128.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.128.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.128.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.129.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.129.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.129.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.13.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.13.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.13.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.130.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.130.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.130.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.131.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.131.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.131.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.132.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.132.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.132.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.133.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.133.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.133.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.134.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.134.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.134.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.135.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.135.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.135.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.136.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.136.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.136.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.137.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.137.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.137.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.138.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.138.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.138.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.139.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.139.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.139.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.14.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.14.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.14.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.140.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.140.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.140.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.141.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.141.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.141.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.142.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.142.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.142.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.143.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.143.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.143.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.144.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.144.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.144.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.145.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.145.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.145.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.146.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.146.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.146.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.147.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.147.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.147.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.148.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.148.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.148.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.149.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.149.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.149.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.15.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.15.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.15.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.150.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.150.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.150.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.151.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.151.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.151.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.152.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.152.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.152.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.153.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.153.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.153.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.154.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.154.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.154.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.155.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.155.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.155.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.156.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.156.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.156.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.157.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.157.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.157.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.158.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.158.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.158.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.159.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.159.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.159.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.16.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.16.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.16.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.17.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.17.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.17.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.18.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.18.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.18.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.19.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.19.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.19.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.2.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.2.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.2.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.20.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.20.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.20.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.21.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.21.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.21.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.22.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.22.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.22.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.23.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.23.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.23.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.24.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.24.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.24.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.25.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.25.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.25.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.26.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.26.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.26.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.27.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.27.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.27.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.28.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.28.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.28.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.29.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.29.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.29.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.3.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.3.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.3.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.30.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.30.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.30.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.31.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.31.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.31.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.32.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.32.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.32.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.33.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.33.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.33.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.34.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.34.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.34.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.35.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.35.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.35.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.36.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.36.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.36.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.37.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.37.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.37.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.38.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.38.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.38.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.39.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.39.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.39.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.4.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.4.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.4.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.40.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.40.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.40.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.41.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.41.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.41.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.42.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.42.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.42.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.43.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.43.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.43.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.44.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.44.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.44.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.45.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.45.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.45.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.46.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.46.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.46.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.47.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.47.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.47.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.48.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.48.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.48.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.49.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.49.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.49.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.5.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.5.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.5.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.50.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.50.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.50.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.51.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.51.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.51.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.52.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.52.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.52.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.53.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.53.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.53.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.54.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.54.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.54.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.55.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.55.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.55.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.56.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.56.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.56.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.57.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.57.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.57.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.58.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.58.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.58.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.59.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.59.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.59.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.6.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.6.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.6.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.60.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.60.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.60.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.61.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.61.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.61.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.62.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.62.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.62.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.63.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.63.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.63.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.64.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.64.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.64.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.65.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.65.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.65.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.66.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.66.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.66.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.67.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.67.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.67.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.68.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.68.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.68.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.69.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.69.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.69.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.7.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.7.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.7.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.70.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.70.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.70.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.71.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.71.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.71.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.72.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.72.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.72.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.73.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.73.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.73.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.74.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.74.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.74.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.75.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.75.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.75.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.76.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.76.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.76.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.77.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.77.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.77.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.78.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.78.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.78.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.79.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.79.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.79.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.8.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.8.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.8.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.80.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.80.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.80.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.81.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.81.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.81.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.82.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.82.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.82.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.83.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.83.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.83.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.84.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.84.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.84.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.85.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.85.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.85.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.86.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.86.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.86.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.87.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.87.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.87.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.88.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.88.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.88.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.89.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.89.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.89.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.9.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.9.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.9.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.90.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.90.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.90.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.91.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.91.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.91.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.92.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.92.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.92.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.93.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.93.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.93.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.94.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.94.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.94.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.95.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.95.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.95.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.96.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.96.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.96.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.97.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.97.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.97.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.98.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.98.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.98.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.99.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.99.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.experts.99.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.gate.e_score_correction_bias": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.gate.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.shared_experts.down_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.shared_experts.gate_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.mlp.shared_experts.up_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.post_attention_layernorm.weight": "model-00037-of-00092.safetensors", + "model.layers.36.self_attn.k_norm.weight": "model-00037-of-00092.safetensors", + "model.layers.36.self_attn.k_proj.bias": "model-00037-of-00092.safetensors", + "model.layers.36.self_attn.k_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.self_attn.o_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.self_attn.q_norm.weight": "model-00037-of-00092.safetensors", + "model.layers.36.self_attn.q_proj.bias": "model-00037-of-00092.safetensors", + "model.layers.36.self_attn.q_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.36.self_attn.v_proj.bias": "model-00037-of-00092.safetensors", + "model.layers.36.self_attn.v_proj.weight": "model-00037-of-00092.safetensors", + "model.layers.37.input_layernorm.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.0.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.0.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.0.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.1.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.1.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.1.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.10.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.10.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.10.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.100.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.100.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.100.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.101.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.101.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.101.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.102.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.102.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.102.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.103.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.103.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.103.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.104.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.104.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.104.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.105.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.105.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.105.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.106.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.106.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.106.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.107.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.107.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.107.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.108.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.108.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.108.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.109.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.109.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.109.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.11.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.11.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.11.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.110.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.110.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.110.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.111.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.111.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.111.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.112.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.112.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.112.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.113.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.113.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.113.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.114.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.114.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.114.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.115.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.115.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.115.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.116.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.116.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.116.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.117.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.117.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.117.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.118.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.118.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.118.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.119.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.119.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.119.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.12.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.12.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.12.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.120.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.120.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.120.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.121.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.121.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.121.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.122.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.122.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.122.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.123.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.123.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.123.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.124.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.124.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.124.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.125.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.125.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.125.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.126.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.126.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.126.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.127.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.127.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.127.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.128.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.128.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.128.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.129.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.129.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.129.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.13.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.13.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.13.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.130.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.130.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.130.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.131.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.131.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.131.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.132.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.132.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.132.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.133.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.133.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.133.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.134.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.134.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.134.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.135.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.135.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.135.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.136.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.136.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.136.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.137.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.137.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.137.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.138.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.138.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.138.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.139.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.139.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.139.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.14.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.14.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.14.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.140.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.140.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.140.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.141.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.141.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.141.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.142.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.142.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.142.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.143.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.143.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.143.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.144.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.144.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.144.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.145.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.145.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.145.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.146.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.146.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.146.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.147.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.147.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.147.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.148.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.148.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.148.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.149.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.149.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.149.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.15.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.15.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.15.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.150.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.150.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.150.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.151.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.151.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.151.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.152.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.152.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.152.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.153.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.153.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.153.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.154.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.154.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.154.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.155.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.155.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.155.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.156.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.156.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.156.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.157.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.157.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.157.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.158.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.158.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.158.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.159.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.159.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.159.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.16.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.16.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.16.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.17.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.17.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.17.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.18.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.18.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.18.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.19.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.19.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.19.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.2.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.2.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.2.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.20.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.20.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.20.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.21.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.21.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.21.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.22.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.22.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.22.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.23.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.23.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.23.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.24.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.24.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.24.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.25.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.25.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.25.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.26.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.26.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.26.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.27.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.27.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.27.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.28.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.28.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.28.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.29.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.29.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.29.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.3.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.3.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.3.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.30.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.30.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.30.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.31.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.31.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.31.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.32.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.32.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.32.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.33.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.33.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.33.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.34.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.34.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.34.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.35.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.35.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.35.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.36.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.36.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.36.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.37.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.37.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.37.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.38.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.38.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.38.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.39.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.39.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.39.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.4.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.4.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.4.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.40.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.40.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.40.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.41.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.41.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.41.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.42.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.42.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.42.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.43.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.43.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.43.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.44.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.44.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.44.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.45.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.45.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.45.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.46.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.46.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.46.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.47.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.47.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.47.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.48.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.48.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.48.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.49.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.49.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.49.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.5.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.5.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.5.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.50.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.50.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.50.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.51.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.51.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.51.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.52.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.52.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.52.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.53.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.53.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.53.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.54.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.54.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.54.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.55.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.55.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.55.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.56.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.56.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.56.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.57.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.57.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.57.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.58.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.58.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.58.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.59.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.59.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.59.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.6.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.6.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.6.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.60.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.60.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.60.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.61.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.61.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.61.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.62.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.62.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.62.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.63.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.63.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.63.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.64.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.64.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.64.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.65.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.65.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.65.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.66.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.66.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.66.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.67.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.67.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.67.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.68.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.68.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.68.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.69.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.69.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.69.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.7.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.7.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.7.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.70.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.70.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.70.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.71.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.71.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.71.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.72.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.72.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.72.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.73.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.73.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.73.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.74.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.74.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.74.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.75.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.75.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.75.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.76.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.76.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.76.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.77.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.77.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.77.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.78.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.78.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.78.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.79.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.79.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.79.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.8.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.8.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.8.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.80.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.80.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.80.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.81.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.81.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.81.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.82.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.82.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.82.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.83.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.83.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.83.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.84.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.84.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.84.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.85.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.85.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.85.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.86.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.86.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.86.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.87.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.87.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.87.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.88.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.88.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.88.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.89.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.89.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.89.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.9.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.9.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.9.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.90.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.90.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.90.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.91.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.91.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.91.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.92.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.92.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.92.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.93.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.93.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.93.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.94.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.94.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.94.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.95.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.95.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.95.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.96.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.96.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.96.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.97.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.97.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.97.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.98.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.98.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.98.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.99.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.99.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.experts.99.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.gate.e_score_correction_bias": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.gate.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.shared_experts.down_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.shared_experts.gate_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.mlp.shared_experts.up_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.post_attention_layernorm.weight": "model-00038-of-00092.safetensors", + "model.layers.37.self_attn.k_norm.weight": "model-00038-of-00092.safetensors", + "model.layers.37.self_attn.k_proj.bias": "model-00038-of-00092.safetensors", + "model.layers.37.self_attn.k_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.self_attn.o_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.self_attn.q_norm.weight": "model-00038-of-00092.safetensors", + "model.layers.37.self_attn.q_proj.bias": "model-00038-of-00092.safetensors", + "model.layers.37.self_attn.q_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.37.self_attn.v_proj.bias": "model-00038-of-00092.safetensors", + "model.layers.37.self_attn.v_proj.weight": "model-00038-of-00092.safetensors", + "model.layers.38.input_layernorm.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.0.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.0.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.0.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.1.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.1.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.1.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.10.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.10.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.10.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.100.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.100.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.100.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.101.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.101.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.101.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.102.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.102.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.102.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.103.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.103.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.103.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.104.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.104.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.104.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.105.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.105.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.105.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.106.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.106.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.106.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.107.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.107.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.107.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.108.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.108.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.108.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.109.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.109.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.109.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.11.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.11.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.11.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.110.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.110.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.110.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.111.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.111.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.111.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.112.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.112.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.112.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.113.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.113.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.113.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.114.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.114.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.114.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.115.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.115.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.115.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.116.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.116.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.116.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.117.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.117.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.117.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.118.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.118.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.118.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.119.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.119.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.119.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.12.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.12.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.12.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.120.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.120.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.120.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.121.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.121.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.121.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.122.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.122.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.122.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.123.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.123.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.123.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.124.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.124.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.124.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.125.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.125.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.125.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.126.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.126.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.126.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.127.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.127.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.127.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.128.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.128.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.128.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.129.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.129.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.129.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.13.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.13.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.13.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.130.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.130.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.130.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.131.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.131.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.131.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.132.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.132.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.132.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.133.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.133.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.133.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.134.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.134.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.134.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.135.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.135.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.135.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.136.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.136.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.136.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.137.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.137.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.137.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.138.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.138.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.138.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.139.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.139.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.139.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.14.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.14.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.14.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.140.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.140.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.140.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.141.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.141.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.141.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.142.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.142.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.142.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.143.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.143.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.143.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.144.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.144.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.144.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.145.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.145.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.145.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.146.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.146.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.146.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.147.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.147.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.147.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.148.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.148.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.148.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.149.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.149.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.149.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.15.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.15.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.15.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.150.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.150.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.150.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.151.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.151.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.151.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.152.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.152.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.152.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.153.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.153.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.153.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.154.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.154.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.154.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.155.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.155.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.155.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.156.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.156.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.156.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.157.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.157.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.157.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.158.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.158.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.158.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.159.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.159.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.159.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.16.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.16.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.16.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.17.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.17.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.17.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.18.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.18.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.18.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.19.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.19.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.19.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.2.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.2.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.2.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.20.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.20.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.20.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.21.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.21.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.21.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.22.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.22.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.22.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.23.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.23.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.23.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.24.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.24.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.24.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.25.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.25.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.25.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.26.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.26.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.26.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.27.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.27.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.27.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.28.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.28.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.28.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.29.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.29.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.29.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.3.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.3.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.3.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.30.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.30.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.30.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.31.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.31.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.31.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.32.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.32.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.32.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.33.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.33.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.33.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.34.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.34.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.34.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.35.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.35.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.35.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.36.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.36.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.36.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.37.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.37.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.37.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.38.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.38.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.38.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.39.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.39.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.39.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.4.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.4.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.4.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.40.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.40.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.40.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.41.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.41.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.41.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.42.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.42.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.42.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.43.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.43.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.43.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.44.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.44.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.44.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.45.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.45.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.45.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.46.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.46.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.46.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.47.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.47.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.47.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.48.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.48.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.48.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.49.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.49.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.49.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.5.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.5.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.5.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.50.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.50.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.50.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.51.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.51.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.51.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.52.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.52.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.52.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.53.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.53.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.53.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.54.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.54.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.54.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.55.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.55.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.55.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.56.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.56.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.56.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.57.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.57.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.57.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.58.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.58.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.58.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.59.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.59.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.59.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.6.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.6.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.6.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.60.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.60.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.60.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.61.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.61.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.61.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.62.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.62.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.62.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.63.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.63.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.63.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.64.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.64.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.64.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.65.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.65.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.65.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.66.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.66.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.66.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.67.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.67.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.67.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.68.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.68.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.68.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.69.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.69.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.69.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.7.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.7.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.7.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.70.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.70.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.70.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.71.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.71.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.71.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.72.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.72.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.72.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.73.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.73.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.73.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.74.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.74.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.74.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.75.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.75.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.75.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.76.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.76.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.76.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.77.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.77.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.77.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.78.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.78.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.78.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.79.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.79.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.79.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.8.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.8.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.8.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.80.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.80.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.80.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.81.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.81.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.81.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.82.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.82.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.82.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.83.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.83.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.83.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.84.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.84.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.84.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.85.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.85.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.85.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.86.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.86.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.86.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.87.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.87.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.87.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.88.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.88.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.88.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.89.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.89.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.89.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.9.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.9.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.9.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.90.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.90.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.90.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.91.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.91.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.91.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.92.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.92.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.92.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.93.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.93.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.93.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.94.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.94.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.94.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.95.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.95.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.95.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.96.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.96.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.96.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.97.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.97.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.97.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.98.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.98.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.98.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.99.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.99.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.experts.99.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.gate.e_score_correction_bias": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.gate.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.shared_experts.down_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.shared_experts.gate_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.mlp.shared_experts.up_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.post_attention_layernorm.weight": "model-00039-of-00092.safetensors", + "model.layers.38.self_attn.k_norm.weight": "model-00039-of-00092.safetensors", + "model.layers.38.self_attn.k_proj.bias": "model-00039-of-00092.safetensors", + "model.layers.38.self_attn.k_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.self_attn.o_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.self_attn.q_norm.weight": "model-00039-of-00092.safetensors", + "model.layers.38.self_attn.q_proj.bias": "model-00039-of-00092.safetensors", + "model.layers.38.self_attn.q_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.38.self_attn.v_proj.bias": "model-00039-of-00092.safetensors", + "model.layers.38.self_attn.v_proj.weight": "model-00039-of-00092.safetensors", + "model.layers.39.input_layernorm.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.0.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.0.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.0.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.1.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.1.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.1.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.10.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.10.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.10.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.100.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.100.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.100.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.101.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.101.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.101.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.102.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.102.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.102.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.103.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.103.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.103.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.104.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.104.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.104.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.105.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.105.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.105.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.106.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.106.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.106.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.107.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.107.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.107.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.108.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.108.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.108.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.109.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.109.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.109.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.11.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.11.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.11.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.110.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.110.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.110.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.111.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.111.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.111.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.112.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.112.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.112.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.113.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.113.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.113.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.114.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.114.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.114.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.115.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.115.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.115.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.116.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.116.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.116.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.117.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.117.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.117.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.118.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.118.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.118.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.119.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.119.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.119.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.12.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.12.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.12.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.120.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.120.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.120.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.121.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.121.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.121.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.122.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.122.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.122.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.123.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.123.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.123.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.124.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.124.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.124.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.125.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.125.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.125.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.126.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.126.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.126.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.127.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.127.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.127.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.128.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.128.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.128.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.129.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.129.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.129.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.13.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.13.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.13.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.130.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.130.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.130.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.131.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.131.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.131.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.132.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.132.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.132.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.133.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.133.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.133.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.134.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.134.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.134.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.135.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.135.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.135.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.136.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.136.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.136.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.137.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.137.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.137.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.138.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.138.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.138.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.139.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.139.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.139.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.14.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.14.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.14.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.140.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.140.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.140.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.141.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.141.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.141.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.142.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.142.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.142.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.143.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.143.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.143.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.144.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.144.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.144.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.145.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.145.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.145.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.146.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.146.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.146.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.147.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.147.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.147.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.148.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.148.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.148.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.149.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.149.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.149.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.15.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.15.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.15.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.150.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.150.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.150.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.151.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.151.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.151.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.152.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.152.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.152.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.153.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.153.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.153.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.154.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.154.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.154.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.155.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.155.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.155.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.156.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.156.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.156.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.157.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.157.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.157.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.158.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.158.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.158.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.159.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.159.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.159.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.16.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.16.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.16.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.17.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.17.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.17.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.18.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.18.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.18.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.19.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.19.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.19.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.2.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.2.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.2.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.20.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.20.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.20.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.21.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.21.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.21.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.22.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.22.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.22.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.23.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.23.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.23.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.24.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.24.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.24.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.25.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.25.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.25.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.26.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.26.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.26.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.27.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.27.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.27.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.28.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.28.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.28.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.29.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.29.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.29.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.3.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.3.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.3.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.30.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.30.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.30.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.31.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.31.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.31.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.32.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.32.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.32.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.33.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.33.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.33.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.34.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.34.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.34.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.35.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.35.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.35.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.36.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.36.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.36.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.37.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.37.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.37.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.38.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.38.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.38.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.39.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.39.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.39.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.4.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.4.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.4.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.40.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.40.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.40.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.41.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.41.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.41.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.42.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.42.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.42.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.43.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.43.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.43.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.44.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.44.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.44.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.45.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.45.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.45.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.46.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.46.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.46.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.47.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.47.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.47.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.48.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.48.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.48.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.49.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.49.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.49.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.5.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.5.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.5.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.50.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.50.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.50.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.51.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.51.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.51.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.52.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.52.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.52.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.53.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.53.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.53.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.54.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.54.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.54.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.55.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.55.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.55.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.56.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.56.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.56.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.57.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.57.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.57.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.58.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.58.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.58.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.59.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.59.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.59.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.6.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.6.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.6.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.60.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.60.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.60.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.61.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.61.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.61.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.62.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.62.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.62.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.63.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.63.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.63.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.64.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.64.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.64.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.65.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.65.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.65.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.66.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.66.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.66.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.67.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.67.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.67.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.68.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.68.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.68.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.69.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.69.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.69.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.7.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.7.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.7.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.70.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.70.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.70.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.71.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.71.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.71.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.72.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.72.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.72.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.73.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.73.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.73.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.74.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.74.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.74.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.75.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.75.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.75.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.76.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.76.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.76.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.77.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.77.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.77.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.78.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.78.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.78.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.79.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.79.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.79.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.8.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.8.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.8.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.80.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.80.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.80.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.81.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.81.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.81.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.82.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.82.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.82.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.83.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.83.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.83.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.84.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.84.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.84.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.85.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.85.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.85.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.86.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.86.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.86.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.87.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.87.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.87.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.88.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.88.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.88.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.89.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.89.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.89.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.9.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.9.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.9.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.90.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.90.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.90.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.91.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.91.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.91.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.92.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.92.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.92.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.93.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.93.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.93.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.94.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.94.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.94.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.95.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.95.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.95.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.96.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.96.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.96.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.97.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.97.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.97.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.98.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.98.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.98.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.99.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.99.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.experts.99.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.gate.e_score_correction_bias": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.gate.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.shared_experts.down_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.shared_experts.gate_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.mlp.shared_experts.up_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.post_attention_layernorm.weight": "model-00040-of-00092.safetensors", + "model.layers.39.self_attn.k_norm.weight": "model-00040-of-00092.safetensors", + "model.layers.39.self_attn.k_proj.bias": "model-00040-of-00092.safetensors", + "model.layers.39.self_attn.k_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.self_attn.o_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.self_attn.q_norm.weight": "model-00040-of-00092.safetensors", + "model.layers.39.self_attn.q_proj.bias": "model-00040-of-00092.safetensors", + "model.layers.39.self_attn.q_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.39.self_attn.v_proj.bias": "model-00040-of-00092.safetensors", + "model.layers.39.self_attn.v_proj.weight": "model-00040-of-00092.safetensors", + "model.layers.40.input_layernorm.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.0.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.0.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.0.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.1.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.1.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.1.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.10.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.10.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.10.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.100.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.100.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.100.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.101.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.101.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.101.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.102.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.102.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.102.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.103.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.103.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.103.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.104.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.104.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.104.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.105.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.105.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.105.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.106.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.106.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.106.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.107.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.107.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.107.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.108.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.108.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.108.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.109.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.109.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.109.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.11.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.11.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.11.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.110.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.110.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.110.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.111.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.111.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.111.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.112.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.112.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.112.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.113.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.113.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.113.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.114.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.114.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.114.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.115.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.115.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.115.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.116.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.116.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.116.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.117.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.117.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.117.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.118.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.118.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.118.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.119.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.119.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.119.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.12.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.12.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.12.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.120.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.120.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.120.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.121.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.121.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.121.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.122.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.122.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.122.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.123.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.123.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.123.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.124.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.124.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.124.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.125.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.125.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.125.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.126.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.126.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.126.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.127.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.127.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.127.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.128.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.128.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.128.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.129.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.129.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.129.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.13.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.13.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.13.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.130.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.130.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.130.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.131.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.131.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.131.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.132.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.132.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.132.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.133.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.133.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.133.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.134.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.134.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.134.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.135.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.135.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.135.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.136.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.136.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.136.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.137.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.137.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.137.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.138.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.138.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.138.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.139.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.139.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.139.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.14.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.14.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.14.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.140.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.140.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.140.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.141.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.141.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.141.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.142.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.142.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.142.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.143.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.143.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.143.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.144.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.144.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.144.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.145.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.145.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.145.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.146.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.146.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.146.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.147.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.147.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.147.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.148.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.148.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.148.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.149.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.149.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.149.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.15.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.15.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.15.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.150.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.150.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.150.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.151.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.151.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.151.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.152.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.152.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.152.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.153.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.153.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.153.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.154.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.154.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.154.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.155.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.155.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.155.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.156.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.156.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.156.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.157.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.157.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.157.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.158.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.158.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.158.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.159.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.159.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.159.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.16.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.16.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.16.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.17.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.17.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.17.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.18.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.18.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.18.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.19.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.19.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.19.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.2.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.2.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.2.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.20.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.20.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.20.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.21.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.21.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.21.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.22.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.22.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.22.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.23.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.23.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.23.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.24.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.24.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.24.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.25.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.25.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.25.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.26.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.26.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.26.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.27.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.27.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.27.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.28.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.28.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.28.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.29.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.29.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.29.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.3.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.3.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.3.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.30.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.30.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.30.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.31.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.31.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.31.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.32.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.32.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.32.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.33.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.33.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.33.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.34.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.34.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.34.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.35.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.35.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.35.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.36.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.36.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.36.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.37.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.37.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.37.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.38.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.38.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.38.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.39.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.39.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.39.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.4.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.4.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.4.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.40.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.40.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.40.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.41.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.41.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.41.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.42.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.42.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.42.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.43.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.43.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.43.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.44.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.44.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.44.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.45.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.45.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.45.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.46.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.46.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.46.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.47.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.47.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.47.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.48.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.48.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.48.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.49.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.49.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.49.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.5.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.5.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.5.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.50.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.50.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.50.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.51.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.51.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.51.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.52.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.52.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.52.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.53.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.53.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.53.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.54.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.54.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.54.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.55.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.55.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.55.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.56.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.56.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.56.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.57.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.57.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.57.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.58.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.58.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.58.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.59.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.59.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.59.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.6.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.6.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.6.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.60.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.60.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.60.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.61.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.61.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.61.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.62.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.62.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.62.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.63.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.63.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.63.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.64.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.64.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.64.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.65.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.65.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.65.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.66.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.66.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.66.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.67.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.67.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.67.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.68.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.68.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.68.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.69.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.69.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.69.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.7.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.7.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.7.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.70.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.70.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.70.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.71.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.71.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.71.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.72.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.72.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.72.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.73.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.73.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.73.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.74.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.74.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.74.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.75.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.75.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.75.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.76.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.76.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.76.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.77.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.77.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.77.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.78.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.78.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.78.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.79.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.79.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.79.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.8.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.8.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.8.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.80.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.80.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.80.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.81.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.81.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.81.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.82.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.82.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.82.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.83.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.83.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.83.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.84.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.84.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.84.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.85.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.85.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.85.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.86.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.86.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.86.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.87.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.87.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.87.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.88.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.88.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.88.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.89.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.89.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.89.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.9.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.9.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.9.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.90.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.90.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.90.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.91.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.91.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.91.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.92.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.92.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.92.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.93.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.93.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.93.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.94.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.94.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.94.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.95.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.95.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.95.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.96.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.96.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.96.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.97.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.97.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.97.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.98.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.98.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.98.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.99.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.99.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.experts.99.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.gate.e_score_correction_bias": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.gate.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.shared_experts.down_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.shared_experts.gate_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.mlp.shared_experts.up_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.post_attention_layernorm.weight": "model-00041-of-00092.safetensors", + "model.layers.40.self_attn.k_norm.weight": "model-00041-of-00092.safetensors", + "model.layers.40.self_attn.k_proj.bias": "model-00041-of-00092.safetensors", + "model.layers.40.self_attn.k_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.self_attn.o_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.self_attn.q_norm.weight": "model-00041-of-00092.safetensors", + "model.layers.40.self_attn.q_proj.bias": "model-00041-of-00092.safetensors", + "model.layers.40.self_attn.q_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.40.self_attn.v_proj.bias": "model-00041-of-00092.safetensors", + "model.layers.40.self_attn.v_proj.weight": "model-00041-of-00092.safetensors", + "model.layers.41.input_layernorm.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.0.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.0.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.0.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.1.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.1.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.1.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.10.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.10.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.10.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.100.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.100.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.100.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.101.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.101.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.101.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.102.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.102.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.102.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.103.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.103.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.103.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.104.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.104.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.104.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.105.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.105.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.105.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.106.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.106.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.106.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.107.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.107.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.107.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.108.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.108.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.108.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.109.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.109.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.109.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.11.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.11.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.11.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.110.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.110.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.110.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.111.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.111.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.111.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.112.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.112.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.112.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.113.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.113.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.113.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.114.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.114.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.114.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.115.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.115.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.115.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.116.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.116.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.116.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.117.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.117.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.117.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.118.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.118.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.118.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.119.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.119.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.119.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.12.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.12.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.12.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.120.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.120.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.120.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.121.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.121.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.121.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.122.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.122.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.122.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.123.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.123.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.123.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.124.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.124.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.124.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.125.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.125.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.125.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.126.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.126.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.126.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.127.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.127.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.127.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.128.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.128.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.128.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.129.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.129.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.129.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.13.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.13.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.13.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.130.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.130.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.130.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.131.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.131.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.131.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.132.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.132.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.132.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.133.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.133.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.133.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.134.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.134.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.134.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.135.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.135.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.135.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.136.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.136.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.136.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.137.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.137.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.137.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.138.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.138.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.138.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.139.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.139.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.139.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.14.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.14.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.14.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.140.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.140.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.140.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.141.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.141.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.141.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.142.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.142.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.142.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.143.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.143.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.143.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.144.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.144.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.144.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.145.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.145.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.145.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.146.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.146.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.146.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.147.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.147.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.147.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.148.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.148.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.148.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.149.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.149.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.149.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.15.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.15.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.15.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.150.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.150.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.150.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.151.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.151.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.151.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.152.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.152.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.152.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.153.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.153.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.153.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.154.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.154.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.154.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.155.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.155.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.155.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.156.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.156.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.156.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.157.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.157.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.157.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.158.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.158.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.158.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.159.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.159.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.159.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.16.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.16.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.16.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.17.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.17.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.17.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.18.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.18.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.18.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.19.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.19.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.19.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.2.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.2.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.2.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.20.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.20.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.20.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.21.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.21.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.21.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.22.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.22.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.22.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.23.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.23.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.23.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.24.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.24.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.24.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.25.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.25.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.25.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.26.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.26.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.26.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.27.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.27.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.27.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.28.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.28.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.28.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.29.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.29.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.29.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.3.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.3.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.3.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.30.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.30.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.30.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.31.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.31.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.31.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.32.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.32.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.32.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.33.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.33.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.33.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.34.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.34.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.34.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.35.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.35.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.35.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.36.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.36.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.36.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.37.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.37.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.37.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.38.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.38.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.38.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.39.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.39.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.39.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.4.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.4.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.4.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.40.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.40.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.40.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.41.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.41.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.41.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.42.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.42.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.42.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.43.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.43.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.43.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.44.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.44.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.44.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.45.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.45.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.45.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.46.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.46.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.46.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.47.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.47.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.47.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.48.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.48.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.48.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.49.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.49.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.49.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.5.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.5.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.5.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.50.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.50.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.50.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.51.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.51.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.51.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.52.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.52.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.52.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.53.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.53.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.53.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.54.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.54.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.54.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.55.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.55.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.55.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.56.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.56.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.56.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.57.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.57.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.57.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.58.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.58.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.58.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.59.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.59.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.59.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.6.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.6.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.6.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.60.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.60.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.60.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.61.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.61.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.61.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.62.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.62.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.62.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.63.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.63.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.63.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.64.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.64.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.64.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.65.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.65.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.65.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.66.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.66.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.66.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.67.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.67.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.67.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.68.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.68.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.68.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.69.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.69.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.69.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.7.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.7.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.7.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.70.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.70.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.70.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.71.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.71.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.71.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.72.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.72.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.72.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.73.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.73.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.73.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.74.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.74.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.74.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.75.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.75.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.75.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.76.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.76.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.76.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.77.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.77.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.77.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.78.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.78.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.78.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.79.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.79.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.79.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.8.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.8.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.8.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.80.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.80.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.80.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.81.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.81.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.81.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.82.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.82.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.82.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.83.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.83.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.83.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.84.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.84.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.84.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.85.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.85.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.85.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.86.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.86.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.86.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.87.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.87.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.87.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.88.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.88.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.88.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.89.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.89.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.89.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.9.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.9.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.9.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.90.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.90.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.90.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.91.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.91.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.91.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.92.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.92.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.92.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.93.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.93.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.93.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.94.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.94.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.94.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.95.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.95.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.95.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.96.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.96.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.96.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.97.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.97.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.97.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.98.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.98.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.98.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.99.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.99.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.experts.99.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.gate.e_score_correction_bias": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.gate.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.shared_experts.down_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.shared_experts.gate_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.mlp.shared_experts.up_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.post_attention_layernorm.weight": "model-00042-of-00092.safetensors", + "model.layers.41.self_attn.k_norm.weight": "model-00042-of-00092.safetensors", + "model.layers.41.self_attn.k_proj.bias": "model-00042-of-00092.safetensors", + "model.layers.41.self_attn.k_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.self_attn.o_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.self_attn.q_norm.weight": "model-00042-of-00092.safetensors", + "model.layers.41.self_attn.q_proj.bias": "model-00042-of-00092.safetensors", + "model.layers.41.self_attn.q_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.41.self_attn.v_proj.bias": "model-00042-of-00092.safetensors", + "model.layers.41.self_attn.v_proj.weight": "model-00042-of-00092.safetensors", + "model.layers.42.input_layernorm.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.0.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.0.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.0.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.1.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.1.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.1.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.10.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.10.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.10.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.100.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.100.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.100.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.101.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.101.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.101.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.102.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.102.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.102.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.103.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.103.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.103.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.104.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.104.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.104.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.105.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.105.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.105.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.106.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.106.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.106.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.107.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.107.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.107.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.108.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.108.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.108.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.109.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.109.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.109.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.11.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.11.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.11.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.110.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.110.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.110.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.111.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.111.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.111.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.112.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.112.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.112.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.113.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.113.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.113.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.114.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.114.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.114.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.115.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.115.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.115.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.116.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.116.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.116.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.117.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.117.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.117.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.118.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.118.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.118.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.119.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.119.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.119.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.12.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.12.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.12.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.120.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.120.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.120.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.121.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.121.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.121.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.122.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.122.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.122.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.123.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.123.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.123.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.124.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.124.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.124.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.125.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.125.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.125.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.126.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.126.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.126.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.127.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.127.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.127.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.128.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.128.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.128.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.129.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.129.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.129.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.13.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.13.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.13.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.130.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.130.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.130.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.131.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.131.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.131.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.132.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.132.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.132.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.133.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.133.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.133.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.134.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.134.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.134.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.135.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.135.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.135.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.136.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.136.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.136.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.137.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.137.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.137.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.138.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.138.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.138.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.139.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.139.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.139.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.14.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.14.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.14.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.140.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.140.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.140.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.141.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.141.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.141.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.142.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.142.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.142.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.143.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.143.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.143.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.144.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.144.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.144.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.145.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.145.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.145.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.146.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.146.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.146.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.147.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.147.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.147.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.148.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.148.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.148.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.149.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.149.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.149.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.15.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.15.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.15.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.150.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.150.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.150.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.151.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.151.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.151.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.152.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.152.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.152.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.153.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.153.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.153.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.154.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.154.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.154.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.155.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.155.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.155.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.156.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.156.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.156.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.157.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.157.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.157.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.158.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.158.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.158.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.159.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.159.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.159.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.16.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.16.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.16.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.17.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.17.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.17.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.18.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.18.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.18.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.19.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.19.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.19.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.2.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.2.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.2.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.20.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.20.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.20.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.21.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.21.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.21.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.22.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.22.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.22.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.23.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.23.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.23.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.24.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.24.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.24.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.25.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.25.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.25.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.26.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.26.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.26.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.27.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.27.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.27.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.28.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.28.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.28.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.29.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.29.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.29.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.3.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.3.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.3.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.30.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.30.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.30.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.31.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.31.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.31.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.32.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.32.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.32.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.33.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.33.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.33.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.34.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.34.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.34.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.35.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.35.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.35.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.36.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.36.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.36.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.37.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.37.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.37.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.38.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.38.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.38.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.39.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.39.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.39.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.4.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.4.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.4.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.40.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.40.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.40.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.41.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.41.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.41.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.42.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.42.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.42.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.43.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.43.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.43.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.44.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.44.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.44.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.45.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.45.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.45.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.46.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.46.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.46.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.47.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.47.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.47.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.48.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.48.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.48.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.49.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.49.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.49.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.5.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.5.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.5.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.50.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.50.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.50.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.51.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.51.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.51.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.52.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.52.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.52.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.53.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.53.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.53.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.54.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.54.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.54.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.55.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.55.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.55.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.56.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.56.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.56.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.57.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.57.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.57.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.58.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.58.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.58.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.59.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.59.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.59.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.6.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.6.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.6.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.60.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.60.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.60.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.61.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.61.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.61.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.62.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.62.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.62.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.63.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.63.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.63.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.64.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.64.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.64.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.65.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.65.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.65.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.66.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.66.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.66.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.67.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.67.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.67.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.68.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.68.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.68.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.69.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.69.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.69.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.7.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.7.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.7.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.70.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.70.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.70.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.71.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.71.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.71.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.72.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.72.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.72.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.73.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.73.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.73.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.74.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.74.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.74.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.75.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.75.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.75.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.76.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.76.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.76.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.77.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.77.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.77.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.78.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.78.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.78.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.79.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.79.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.79.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.8.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.8.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.8.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.80.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.80.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.80.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.81.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.81.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.81.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.82.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.82.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.82.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.83.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.83.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.83.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.84.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.84.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.84.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.85.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.85.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.85.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.86.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.86.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.86.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.87.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.87.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.87.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.88.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.88.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.88.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.89.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.89.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.89.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.9.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.9.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.9.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.90.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.90.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.90.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.91.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.91.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.91.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.92.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.92.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.92.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.93.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.93.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.93.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.94.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.94.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.94.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.95.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.95.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.95.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.96.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.96.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.96.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.97.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.97.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.97.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.98.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.98.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.98.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.99.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.99.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.experts.99.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.gate.e_score_correction_bias": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.gate.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.shared_experts.down_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.shared_experts.gate_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.mlp.shared_experts.up_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.post_attention_layernorm.weight": "model-00043-of-00092.safetensors", + "model.layers.42.self_attn.k_norm.weight": "model-00043-of-00092.safetensors", + "model.layers.42.self_attn.k_proj.bias": "model-00043-of-00092.safetensors", + "model.layers.42.self_attn.k_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.self_attn.o_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.self_attn.q_norm.weight": "model-00043-of-00092.safetensors", + "model.layers.42.self_attn.q_proj.bias": "model-00043-of-00092.safetensors", + "model.layers.42.self_attn.q_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.42.self_attn.v_proj.bias": "model-00043-of-00092.safetensors", + "model.layers.42.self_attn.v_proj.weight": "model-00043-of-00092.safetensors", + "model.layers.43.input_layernorm.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.0.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.0.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.0.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.1.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.1.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.1.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.10.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.10.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.10.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.100.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.100.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.100.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.101.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.101.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.101.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.102.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.102.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.102.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.103.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.103.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.103.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.104.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.104.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.104.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.105.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.105.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.105.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.106.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.106.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.106.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.107.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.107.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.107.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.108.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.108.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.108.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.109.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.109.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.109.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.11.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.11.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.11.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.110.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.110.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.110.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.111.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.111.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.111.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.112.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.112.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.112.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.113.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.113.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.113.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.114.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.114.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.114.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.115.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.115.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.115.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.116.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.116.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.116.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.117.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.117.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.117.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.118.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.118.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.118.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.119.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.119.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.119.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.12.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.12.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.12.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.120.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.120.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.120.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.121.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.121.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.121.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.122.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.122.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.122.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.123.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.123.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.123.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.124.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.124.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.124.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.125.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.125.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.125.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.126.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.126.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.126.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.127.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.127.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.127.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.128.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.128.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.128.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.129.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.129.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.129.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.13.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.13.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.13.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.130.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.130.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.130.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.131.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.131.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.131.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.132.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.132.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.132.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.133.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.133.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.133.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.134.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.134.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.134.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.135.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.135.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.135.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.136.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.136.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.136.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.137.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.137.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.137.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.138.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.138.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.138.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.139.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.139.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.139.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.14.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.14.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.14.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.140.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.140.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.140.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.141.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.141.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.141.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.142.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.142.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.142.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.143.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.143.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.143.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.144.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.144.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.144.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.145.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.145.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.145.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.146.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.146.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.146.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.147.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.147.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.147.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.148.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.148.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.148.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.149.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.149.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.149.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.15.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.15.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.15.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.150.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.150.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.150.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.151.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.151.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.151.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.152.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.152.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.152.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.153.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.153.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.153.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.154.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.154.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.154.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.155.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.155.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.155.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.156.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.156.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.156.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.157.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.157.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.157.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.158.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.158.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.158.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.159.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.159.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.159.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.16.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.16.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.16.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.17.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.17.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.17.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.18.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.18.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.18.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.19.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.19.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.19.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.2.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.2.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.2.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.20.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.20.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.20.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.21.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.21.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.21.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.22.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.22.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.22.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.23.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.23.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.23.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.24.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.24.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.24.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.25.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.25.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.25.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.26.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.26.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.26.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.27.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.27.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.27.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.28.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.28.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.28.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.29.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.29.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.29.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.3.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.3.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.3.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.30.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.30.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.30.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.31.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.31.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.31.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.32.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.32.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.32.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.33.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.33.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.33.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.34.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.34.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.34.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.35.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.35.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.35.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.36.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.36.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.36.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.37.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.37.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.37.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.38.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.38.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.38.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.39.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.39.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.39.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.4.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.4.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.4.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.40.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.40.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.40.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.41.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.41.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.41.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.42.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.42.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.42.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.43.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.43.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.43.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.44.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.44.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.44.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.45.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.45.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.45.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.46.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.46.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.46.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.47.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.47.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.47.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.48.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.48.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.48.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.49.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.49.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.49.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.5.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.5.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.5.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.50.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.50.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.50.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.51.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.51.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.51.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.52.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.52.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.52.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.53.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.53.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.53.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.54.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.54.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.54.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.55.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.55.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.55.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.56.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.56.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.56.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.57.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.57.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.57.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.58.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.58.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.58.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.59.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.59.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.59.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.6.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.6.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.6.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.60.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.60.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.60.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.61.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.61.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.61.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.62.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.62.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.62.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.63.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.63.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.63.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.64.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.64.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.64.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.65.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.65.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.65.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.66.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.66.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.66.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.67.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.67.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.67.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.68.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.68.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.68.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.69.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.69.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.69.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.7.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.7.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.7.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.70.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.70.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.70.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.71.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.71.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.71.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.72.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.72.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.72.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.73.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.73.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.73.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.74.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.74.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.74.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.75.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.75.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.75.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.76.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.76.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.76.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.77.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.77.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.77.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.78.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.78.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.78.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.79.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.79.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.79.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.8.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.8.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.8.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.80.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.80.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.80.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.81.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.81.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.81.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.82.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.82.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.82.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.83.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.83.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.83.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.84.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.84.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.84.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.85.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.85.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.85.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.86.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.86.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.86.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.87.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.87.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.87.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.88.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.88.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.88.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.89.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.89.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.89.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.9.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.9.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.9.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.90.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.90.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.90.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.91.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.91.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.91.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.92.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.92.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.92.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.93.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.93.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.93.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.94.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.94.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.94.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.95.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.95.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.95.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.96.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.96.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.96.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.97.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.97.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.97.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.98.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.98.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.98.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.99.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.99.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.experts.99.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.gate.e_score_correction_bias": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.gate.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.shared_experts.down_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.shared_experts.gate_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.mlp.shared_experts.up_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.post_attention_layernorm.weight": "model-00044-of-00092.safetensors", + "model.layers.43.self_attn.k_norm.weight": "model-00044-of-00092.safetensors", + "model.layers.43.self_attn.k_proj.bias": "model-00044-of-00092.safetensors", + "model.layers.43.self_attn.k_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.self_attn.o_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.self_attn.q_norm.weight": "model-00044-of-00092.safetensors", + "model.layers.43.self_attn.q_proj.bias": "model-00044-of-00092.safetensors", + "model.layers.43.self_attn.q_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.43.self_attn.v_proj.bias": "model-00044-of-00092.safetensors", + "model.layers.43.self_attn.v_proj.weight": "model-00044-of-00092.safetensors", + "model.layers.44.input_layernorm.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.0.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.0.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.0.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.1.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.1.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.1.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.10.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.10.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.10.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.100.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.100.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.100.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.101.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.101.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.101.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.102.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.102.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.102.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.103.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.103.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.103.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.104.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.104.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.104.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.105.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.105.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.105.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.106.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.106.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.106.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.107.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.107.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.107.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.108.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.108.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.108.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.109.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.109.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.109.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.11.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.11.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.11.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.110.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.110.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.110.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.111.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.111.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.111.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.112.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.112.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.112.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.113.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.113.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.113.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.114.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.114.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.114.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.115.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.115.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.115.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.116.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.116.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.116.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.117.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.117.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.117.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.118.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.118.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.118.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.119.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.119.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.119.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.12.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.12.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.12.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.120.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.120.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.120.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.121.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.121.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.121.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.122.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.122.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.122.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.123.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.123.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.123.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.124.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.124.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.124.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.125.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.125.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.125.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.126.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.126.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.126.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.127.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.127.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.127.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.128.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.128.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.128.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.129.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.129.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.129.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.13.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.13.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.13.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.130.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.130.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.130.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.131.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.131.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.131.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.132.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.132.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.132.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.133.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.133.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.133.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.134.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.134.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.134.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.135.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.135.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.135.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.136.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.136.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.136.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.137.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.137.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.137.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.138.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.138.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.138.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.139.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.139.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.139.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.14.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.14.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.14.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.140.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.140.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.140.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.141.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.141.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.141.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.142.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.142.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.142.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.143.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.143.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.143.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.144.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.144.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.144.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.145.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.145.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.145.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.146.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.146.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.146.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.147.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.147.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.147.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.148.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.148.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.148.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.149.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.149.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.149.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.15.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.15.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.15.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.150.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.150.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.150.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.151.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.151.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.151.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.152.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.152.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.152.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.153.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.153.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.153.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.154.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.154.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.154.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.155.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.155.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.155.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.156.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.156.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.156.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.157.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.157.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.157.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.158.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.158.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.158.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.159.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.159.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.159.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.16.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.16.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.16.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.17.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.17.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.17.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.18.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.18.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.18.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.19.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.19.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.19.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.2.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.2.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.2.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.20.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.20.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.20.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.21.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.21.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.21.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.22.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.22.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.22.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.23.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.23.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.23.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.24.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.24.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.24.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.25.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.25.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.25.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.26.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.26.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.26.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.27.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.27.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.27.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.28.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.28.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.28.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.29.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.29.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.29.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.3.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.3.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.3.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.30.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.30.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.30.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.31.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.31.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.31.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.32.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.32.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.32.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.33.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.33.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.33.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.34.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.34.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.34.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.35.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.35.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.35.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.36.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.36.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.36.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.37.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.37.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.37.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.38.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.38.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.38.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.39.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.39.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.39.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.4.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.4.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.4.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.40.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.40.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.40.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.41.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.41.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.41.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.42.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.42.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.42.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.43.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.43.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.43.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.44.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.44.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.44.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.45.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.45.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.45.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.46.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.46.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.46.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.47.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.47.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.47.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.48.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.48.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.48.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.49.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.49.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.49.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.5.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.5.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.5.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.50.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.50.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.50.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.51.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.51.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.51.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.52.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.52.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.52.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.53.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.53.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.53.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.54.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.54.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.54.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.55.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.55.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.55.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.56.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.56.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.56.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.57.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.57.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.57.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.58.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.58.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.58.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.59.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.59.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.59.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.6.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.6.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.6.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.60.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.60.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.60.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.61.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.61.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.61.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.62.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.62.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.62.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.63.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.63.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.63.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.64.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.64.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.64.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.65.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.65.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.65.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.66.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.66.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.66.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.67.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.67.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.67.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.68.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.68.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.68.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.69.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.69.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.69.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.7.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.7.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.7.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.70.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.70.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.70.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.71.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.71.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.71.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.72.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.72.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.72.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.73.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.73.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.73.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.74.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.74.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.74.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.75.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.75.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.75.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.76.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.76.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.76.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.77.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.77.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.77.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.78.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.78.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.78.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.79.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.79.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.79.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.8.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.8.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.8.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.80.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.80.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.80.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.81.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.81.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.81.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.82.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.82.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.82.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.83.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.83.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.83.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.84.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.84.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.84.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.85.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.85.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.85.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.86.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.86.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.86.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.87.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.87.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.87.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.88.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.88.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.88.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.89.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.89.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.89.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.9.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.9.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.9.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.90.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.90.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.90.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.91.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.91.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.91.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.92.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.92.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.92.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.93.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.93.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.93.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.94.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.94.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.94.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.95.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.95.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.95.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.96.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.96.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.96.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.97.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.97.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.97.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.98.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.98.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.98.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.99.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.99.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.experts.99.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.gate.e_score_correction_bias": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.gate.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.shared_experts.down_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.shared_experts.gate_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.mlp.shared_experts.up_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.post_attention_layernorm.weight": "model-00045-of-00092.safetensors", + "model.layers.44.self_attn.k_norm.weight": "model-00045-of-00092.safetensors", + "model.layers.44.self_attn.k_proj.bias": "model-00045-of-00092.safetensors", + "model.layers.44.self_attn.k_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.self_attn.o_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.self_attn.q_norm.weight": "model-00045-of-00092.safetensors", + "model.layers.44.self_attn.q_proj.bias": "model-00045-of-00092.safetensors", + "model.layers.44.self_attn.q_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.44.self_attn.v_proj.bias": "model-00045-of-00092.safetensors", + "model.layers.44.self_attn.v_proj.weight": "model-00045-of-00092.safetensors", + "model.layers.45.input_layernorm.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.0.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.0.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.0.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.1.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.1.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.1.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.10.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.10.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.10.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.100.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.100.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.100.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.101.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.101.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.101.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.102.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.102.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.102.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.103.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.103.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.103.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.104.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.104.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.104.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.105.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.105.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.105.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.106.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.106.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.106.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.107.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.107.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.107.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.108.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.108.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.108.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.109.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.109.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.109.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.11.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.11.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.11.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.110.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.110.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.110.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.111.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.111.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.111.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.112.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.112.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.112.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.113.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.113.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.113.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.114.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.114.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.114.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.115.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.115.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.115.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.116.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.116.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.116.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.117.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.117.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.117.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.118.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.118.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.118.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.119.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.119.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.119.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.12.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.12.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.12.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.120.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.120.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.120.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.121.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.121.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.121.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.122.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.122.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.122.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.123.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.123.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.123.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.124.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.124.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.124.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.125.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.125.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.125.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.126.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.126.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.126.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.127.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.127.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.127.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.128.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.128.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.128.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.129.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.129.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.129.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.13.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.13.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.13.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.130.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.130.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.130.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.131.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.131.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.131.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.132.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.132.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.132.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.133.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.133.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.133.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.134.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.134.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.134.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.135.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.135.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.135.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.136.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.136.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.136.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.137.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.137.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.137.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.138.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.138.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.138.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.139.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.139.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.139.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.14.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.14.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.14.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.140.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.140.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.140.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.141.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.141.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.141.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.142.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.142.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.142.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.143.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.143.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.143.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.144.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.144.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.144.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.145.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.145.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.145.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.146.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.146.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.146.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.147.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.147.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.147.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.148.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.148.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.148.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.149.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.149.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.149.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.15.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.15.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.15.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.150.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.150.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.150.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.151.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.151.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.151.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.152.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.152.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.152.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.153.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.153.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.153.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.154.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.154.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.154.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.155.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.155.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.155.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.156.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.156.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.156.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.157.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.157.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.157.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.158.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.158.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.158.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.159.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.159.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.159.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.16.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.16.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.16.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.17.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.17.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.17.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.18.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.18.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.18.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.19.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.19.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.19.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.2.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.2.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.2.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.20.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.20.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.20.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.21.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.21.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.21.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.22.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.22.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.22.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.23.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.23.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.23.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.24.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.24.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.24.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.25.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.25.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.25.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.26.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.26.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.26.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.27.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.27.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.27.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.28.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.28.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.28.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.29.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.29.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.29.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.3.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.3.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.3.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.30.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.30.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.30.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.31.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.31.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.31.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.32.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.32.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.32.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.33.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.33.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.33.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.34.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.34.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.34.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.35.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.35.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.35.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.36.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.36.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.36.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.37.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.37.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.37.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.38.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.38.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.38.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.39.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.39.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.39.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.4.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.4.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.4.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.40.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.40.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.40.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.41.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.41.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.41.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.42.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.42.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.42.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.43.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.43.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.43.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.44.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.44.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.44.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.45.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.45.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.45.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.46.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.46.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.46.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.47.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.47.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.47.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.48.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.48.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.48.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.49.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.49.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.49.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.5.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.5.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.5.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.50.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.50.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.50.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.51.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.51.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.51.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.52.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.52.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.52.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.53.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.53.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.53.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.54.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.54.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.54.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.55.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.55.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.55.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.56.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.56.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.56.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.57.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.57.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.57.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.58.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.58.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.58.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.59.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.59.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.59.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.6.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.6.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.6.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.60.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.60.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.60.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.61.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.61.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.61.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.62.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.62.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.62.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.63.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.63.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.63.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.64.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.64.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.64.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.65.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.65.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.65.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.66.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.66.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.66.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.67.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.67.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.67.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.68.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.68.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.68.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.69.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.69.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.69.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.7.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.7.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.7.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.70.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.70.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.70.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.71.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.71.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.71.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.72.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.72.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.72.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.73.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.73.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.73.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.74.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.74.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.74.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.75.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.75.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.75.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.76.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.76.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.76.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.77.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.77.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.77.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.78.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.78.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.78.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.79.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.79.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.79.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.8.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.8.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.8.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.80.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.80.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.80.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.81.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.81.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.81.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.82.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.82.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.82.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.83.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.83.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.83.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.84.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.84.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.84.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.85.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.85.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.85.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.86.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.86.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.86.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.87.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.87.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.87.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.88.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.88.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.88.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.89.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.89.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.89.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.9.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.9.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.9.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.90.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.90.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.90.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.91.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.91.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.91.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.92.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.92.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.92.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.93.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.93.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.93.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.94.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.94.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.94.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.95.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.95.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.95.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.96.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.96.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.96.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.97.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.97.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.97.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.98.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.98.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.98.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.99.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.99.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.experts.99.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.gate.e_score_correction_bias": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.gate.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.shared_experts.down_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.shared_experts.gate_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.mlp.shared_experts.up_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.post_attention_layernorm.weight": "model-00046-of-00092.safetensors", + "model.layers.45.self_attn.k_norm.weight": "model-00046-of-00092.safetensors", + "model.layers.45.self_attn.k_proj.bias": "model-00046-of-00092.safetensors", + "model.layers.45.self_attn.k_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.self_attn.o_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.self_attn.q_norm.weight": "model-00046-of-00092.safetensors", + "model.layers.45.self_attn.q_proj.bias": "model-00046-of-00092.safetensors", + "model.layers.45.self_attn.q_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.45.self_attn.v_proj.bias": "model-00046-of-00092.safetensors", + "model.layers.45.self_attn.v_proj.weight": "model-00046-of-00092.safetensors", + "model.layers.46.input_layernorm.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.0.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.0.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.0.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.1.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.1.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.1.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.10.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.10.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.10.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.100.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.100.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.100.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.101.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.101.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.101.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.102.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.102.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.102.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.103.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.103.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.103.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.104.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.104.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.104.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.105.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.105.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.105.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.106.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.106.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.106.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.107.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.107.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.107.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.108.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.108.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.108.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.109.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.109.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.109.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.11.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.11.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.11.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.110.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.110.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.110.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.111.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.111.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.111.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.112.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.112.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.112.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.113.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.113.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.113.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.114.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.114.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.114.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.115.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.115.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.115.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.116.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.116.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.116.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.117.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.117.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.117.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.118.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.118.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.118.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.119.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.119.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.119.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.12.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.12.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.12.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.120.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.120.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.120.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.121.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.121.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.121.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.122.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.122.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.122.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.123.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.123.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.123.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.124.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.124.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.124.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.125.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.125.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.125.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.126.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.126.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.126.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.127.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.127.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.127.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.128.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.128.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.128.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.129.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.129.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.129.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.13.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.13.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.13.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.130.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.130.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.130.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.131.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.131.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.131.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.132.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.132.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.132.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.133.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.133.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.133.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.134.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.134.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.134.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.135.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.135.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.135.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.136.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.136.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.136.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.137.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.137.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.137.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.138.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.138.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.138.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.139.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.139.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.139.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.14.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.14.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.14.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.140.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.140.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.140.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.141.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.141.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.141.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.142.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.142.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.142.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.143.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.143.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.143.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.144.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.144.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.144.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.145.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.145.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.145.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.146.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.146.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.146.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.147.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.147.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.147.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.148.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.148.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.148.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.149.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.149.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.149.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.15.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.15.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.15.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.150.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.150.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.150.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.151.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.151.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.151.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.152.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.152.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.152.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.153.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.153.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.153.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.154.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.154.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.154.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.155.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.155.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.155.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.156.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.156.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.156.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.157.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.157.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.157.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.158.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.158.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.158.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.159.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.159.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.159.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.16.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.16.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.16.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.17.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.17.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.17.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.18.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.18.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.18.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.19.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.19.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.19.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.2.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.2.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.2.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.20.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.20.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.20.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.21.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.21.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.21.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.22.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.22.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.22.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.23.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.23.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.23.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.24.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.24.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.24.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.25.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.25.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.25.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.26.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.26.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.26.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.27.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.27.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.27.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.28.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.28.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.28.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.29.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.29.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.29.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.3.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.3.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.3.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.30.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.30.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.30.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.31.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.31.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.31.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.32.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.32.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.32.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.33.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.33.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.33.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.34.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.34.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.34.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.35.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.35.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.35.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.36.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.36.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.36.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.37.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.37.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.37.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.38.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.38.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.38.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.39.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.39.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.39.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.4.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.4.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.4.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.40.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.40.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.40.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.41.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.41.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.41.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.42.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.42.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.42.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.43.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.43.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.43.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.44.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.44.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.44.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.45.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.45.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.45.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.46.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.46.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.46.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.47.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.47.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.47.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.48.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.48.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.48.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.49.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.49.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.49.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.5.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.5.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.5.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.50.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.50.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.50.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.51.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.51.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.51.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.52.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.52.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.52.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.53.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.53.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.53.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.54.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.54.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.54.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.55.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.55.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.55.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.56.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.56.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.56.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.57.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.57.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.57.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.58.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.58.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.58.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.59.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.59.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.59.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.6.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.6.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.6.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.60.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.60.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.60.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.61.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.61.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.61.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.62.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.62.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.62.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.63.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.63.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.63.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.64.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.64.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.64.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.65.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.65.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.65.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.66.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.66.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.66.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.67.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.67.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.67.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.68.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.68.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.68.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.69.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.69.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.69.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.7.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.7.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.7.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.70.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.70.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.70.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.71.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.71.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.71.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.72.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.72.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.72.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.73.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.73.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.73.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.74.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.74.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.74.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.75.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.75.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.75.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.76.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.76.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.76.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.77.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.77.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.77.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.78.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.78.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.78.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.79.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.79.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.79.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.8.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.8.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.8.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.80.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.80.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.80.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.81.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.81.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.81.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.82.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.82.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.82.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.83.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.83.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.83.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.84.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.84.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.84.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.85.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.85.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.85.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.86.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.86.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.86.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.87.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.87.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.87.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.88.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.88.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.88.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.89.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.89.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.89.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.9.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.9.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.9.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.90.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.90.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.90.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.91.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.91.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.91.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.92.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.92.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.92.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.93.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.93.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.93.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.94.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.94.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.94.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.95.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.95.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.95.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.96.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.96.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.96.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.97.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.97.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.97.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.98.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.98.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.98.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.99.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.99.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.experts.99.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.gate.e_score_correction_bias": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.gate.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.shared_experts.down_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.shared_experts.gate_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.mlp.shared_experts.up_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.post_attention_layernorm.weight": "model-00047-of-00092.safetensors", + "model.layers.46.self_attn.k_norm.weight": "model-00047-of-00092.safetensors", + "model.layers.46.self_attn.k_proj.bias": "model-00047-of-00092.safetensors", + "model.layers.46.self_attn.k_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.self_attn.o_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.self_attn.q_norm.weight": "model-00047-of-00092.safetensors", + "model.layers.46.self_attn.q_proj.bias": "model-00047-of-00092.safetensors", + "model.layers.46.self_attn.q_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.46.self_attn.v_proj.bias": "model-00047-of-00092.safetensors", + "model.layers.46.self_attn.v_proj.weight": "model-00047-of-00092.safetensors", + "model.layers.47.input_layernorm.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.0.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.0.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.0.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.1.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.1.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.1.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.10.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.10.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.10.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.100.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.100.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.100.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.101.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.101.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.101.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.102.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.102.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.102.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.103.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.103.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.103.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.104.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.104.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.104.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.105.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.105.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.105.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.106.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.106.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.106.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.107.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.107.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.107.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.108.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.108.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.108.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.109.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.109.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.109.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.11.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.11.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.11.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.110.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.110.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.110.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.111.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.111.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.111.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.112.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.112.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.112.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.113.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.113.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.113.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.114.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.114.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.114.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.115.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.115.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.115.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.116.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.116.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.116.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.117.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.117.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.117.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.118.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.118.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.118.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.119.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.119.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.119.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.12.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.12.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.12.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.120.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.120.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.120.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.121.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.121.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.121.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.122.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.122.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.122.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.123.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.123.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.123.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.124.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.124.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.124.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.125.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.125.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.125.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.126.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.126.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.126.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.127.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.127.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.127.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.128.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.128.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.128.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.129.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.129.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.129.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.13.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.13.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.13.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.130.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.130.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.130.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.131.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.131.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.131.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.132.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.132.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.132.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.133.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.133.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.133.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.134.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.134.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.134.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.135.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.135.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.135.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.136.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.136.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.136.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.137.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.137.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.137.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.138.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.138.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.138.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.139.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.139.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.139.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.14.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.14.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.14.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.140.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.140.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.140.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.141.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.141.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.141.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.142.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.142.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.142.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.143.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.143.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.143.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.144.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.144.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.144.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.145.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.145.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.145.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.146.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.146.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.146.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.147.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.147.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.147.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.148.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.148.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.148.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.149.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.149.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.149.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.15.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.15.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.15.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.150.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.150.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.150.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.151.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.151.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.151.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.152.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.152.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.152.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.153.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.153.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.153.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.154.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.154.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.154.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.155.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.155.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.155.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.156.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.156.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.156.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.157.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.157.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.157.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.158.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.158.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.158.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.159.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.159.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.159.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.16.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.16.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.16.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.17.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.17.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.17.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.18.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.18.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.18.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.19.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.19.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.19.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.2.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.2.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.2.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.20.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.20.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.20.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.21.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.21.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.21.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.22.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.22.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.22.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.23.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.23.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.23.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.24.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.24.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.24.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.25.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.25.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.25.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.26.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.26.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.26.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.27.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.27.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.27.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.28.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.28.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.28.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.29.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.29.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.29.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.3.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.3.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.3.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.30.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.30.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.30.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.31.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.31.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.31.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.32.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.32.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.32.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.33.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.33.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.33.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.34.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.34.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.34.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.35.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.35.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.35.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.36.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.36.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.36.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.37.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.37.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.37.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.38.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.38.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.38.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.39.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.39.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.39.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.4.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.4.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.4.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.40.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.40.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.40.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.41.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.41.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.41.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.42.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.42.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.42.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.43.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.43.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.43.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.44.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.44.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.44.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.45.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.45.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.45.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.46.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.46.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.46.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.47.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.47.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.47.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.48.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.48.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.48.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.49.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.49.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.49.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.5.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.5.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.5.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.50.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.50.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.50.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.51.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.51.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.51.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.52.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.52.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.52.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.53.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.53.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.53.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.54.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.54.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.54.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.55.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.55.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.55.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.56.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.56.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.56.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.57.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.57.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.57.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.58.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.58.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.58.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.59.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.59.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.59.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.6.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.6.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.6.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.60.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.60.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.60.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.61.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.61.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.61.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.62.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.62.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.62.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.63.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.63.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.63.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.64.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.64.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.64.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.65.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.65.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.65.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.66.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.66.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.66.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.67.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.67.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.67.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.68.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.68.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.68.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.69.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.69.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.69.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.7.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.7.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.7.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.70.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.70.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.70.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.71.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.71.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.71.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.72.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.72.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.72.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.73.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.73.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.73.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.74.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.74.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.74.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.75.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.75.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.75.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.76.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.76.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.76.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.77.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.77.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.77.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.78.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.78.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.78.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.79.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.79.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.79.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.8.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.8.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.8.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.80.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.80.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.80.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.81.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.81.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.81.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.82.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.82.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.82.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.83.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.83.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.83.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.84.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.84.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.84.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.85.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.85.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.85.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.86.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.86.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.86.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.87.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.87.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.87.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.88.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.88.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.88.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.89.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.89.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.89.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.9.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.9.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.9.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.90.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.90.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.90.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.91.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.91.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.91.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.92.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.92.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.92.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.93.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.93.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.93.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.94.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.94.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.94.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.95.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.95.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.95.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.96.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.96.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.96.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.97.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.97.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.97.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.98.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.98.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.98.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.99.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.99.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.experts.99.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.gate.e_score_correction_bias": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.gate.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.shared_experts.down_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.shared_experts.gate_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.mlp.shared_experts.up_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.post_attention_layernorm.weight": "model-00048-of-00092.safetensors", + "model.layers.47.self_attn.k_norm.weight": "model-00048-of-00092.safetensors", + "model.layers.47.self_attn.k_proj.bias": "model-00048-of-00092.safetensors", + "model.layers.47.self_attn.k_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.self_attn.o_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.self_attn.q_norm.weight": "model-00048-of-00092.safetensors", + "model.layers.47.self_attn.q_proj.bias": "model-00048-of-00092.safetensors", + "model.layers.47.self_attn.q_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.47.self_attn.v_proj.bias": "model-00048-of-00092.safetensors", + "model.layers.47.self_attn.v_proj.weight": "model-00048-of-00092.safetensors", + "model.layers.48.input_layernorm.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.0.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.0.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.0.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.1.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.1.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.1.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.10.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.10.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.10.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.100.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.100.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.100.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.101.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.101.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.101.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.102.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.102.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.102.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.103.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.103.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.103.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.104.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.104.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.104.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.105.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.105.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.105.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.106.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.106.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.106.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.107.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.107.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.107.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.108.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.108.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.108.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.109.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.109.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.109.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.11.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.11.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.11.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.110.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.110.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.110.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.111.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.111.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.111.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.112.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.112.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.112.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.113.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.113.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.113.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.114.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.114.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.114.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.115.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.115.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.115.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.116.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.116.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.116.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.117.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.117.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.117.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.118.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.118.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.118.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.119.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.119.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.119.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.12.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.12.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.12.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.120.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.120.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.120.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.121.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.121.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.121.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.122.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.122.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.122.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.123.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.123.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.123.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.124.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.124.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.124.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.125.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.125.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.125.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.126.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.126.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.126.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.127.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.127.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.127.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.128.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.128.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.128.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.129.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.129.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.129.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.13.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.13.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.13.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.130.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.130.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.130.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.131.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.131.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.131.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.132.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.132.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.132.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.133.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.133.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.133.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.134.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.134.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.134.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.135.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.135.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.135.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.136.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.136.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.136.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.137.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.137.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.137.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.138.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.138.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.138.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.139.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.139.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.139.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.14.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.14.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.14.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.140.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.140.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.140.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.141.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.141.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.141.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.142.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.142.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.142.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.143.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.143.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.143.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.144.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.144.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.144.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.145.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.145.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.145.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.146.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.146.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.146.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.147.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.147.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.147.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.148.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.148.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.148.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.149.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.149.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.149.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.15.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.15.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.15.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.150.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.150.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.150.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.151.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.151.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.151.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.152.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.152.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.152.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.153.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.153.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.153.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.154.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.154.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.154.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.155.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.155.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.155.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.156.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.156.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.156.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.157.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.157.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.157.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.158.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.158.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.158.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.159.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.159.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.159.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.16.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.16.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.16.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.17.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.17.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.17.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.18.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.18.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.18.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.19.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.19.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.19.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.2.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.2.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.2.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.20.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.20.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.20.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.21.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.21.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.21.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.22.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.22.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.22.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.23.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.23.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.23.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.24.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.24.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.24.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.25.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.25.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.25.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.26.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.26.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.26.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.27.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.27.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.27.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.28.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.28.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.28.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.29.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.29.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.29.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.3.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.3.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.3.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.30.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.30.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.30.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.31.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.31.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.31.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.32.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.32.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.32.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.33.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.33.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.33.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.34.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.34.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.34.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.35.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.35.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.35.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.36.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.36.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.36.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.37.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.37.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.37.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.38.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.38.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.38.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.39.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.39.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.39.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.4.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.4.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.4.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.40.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.40.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.40.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.41.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.41.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.41.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.42.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.42.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.42.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.43.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.43.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.43.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.44.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.44.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.44.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.45.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.45.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.45.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.46.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.46.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.46.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.47.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.47.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.47.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.48.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.48.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.48.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.49.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.49.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.49.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.5.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.5.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.5.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.50.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.50.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.50.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.51.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.51.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.51.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.52.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.52.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.52.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.53.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.53.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.53.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.54.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.54.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.54.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.55.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.55.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.55.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.56.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.56.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.56.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.57.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.57.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.57.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.58.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.58.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.58.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.59.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.59.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.59.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.6.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.6.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.6.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.60.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.60.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.60.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.61.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.61.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.61.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.62.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.62.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.62.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.63.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.63.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.63.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.64.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.64.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.64.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.65.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.65.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.65.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.66.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.66.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.66.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.67.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.67.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.67.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.68.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.68.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.68.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.69.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.69.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.69.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.7.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.7.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.7.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.70.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.70.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.70.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.71.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.71.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.71.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.72.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.72.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.72.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.73.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.73.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.73.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.74.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.74.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.74.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.75.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.75.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.75.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.76.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.76.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.76.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.77.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.77.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.77.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.78.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.78.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.78.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.79.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.79.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.79.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.8.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.8.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.8.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.80.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.80.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.80.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.81.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.81.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.81.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.82.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.82.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.82.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.83.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.83.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.83.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.84.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.84.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.84.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.85.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.85.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.85.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.86.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.86.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.86.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.87.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.87.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.87.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.88.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.88.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.88.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.89.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.89.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.89.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.9.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.9.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.9.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.90.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.90.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.90.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.91.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.91.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.91.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.92.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.92.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.92.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.93.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.93.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.93.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.94.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.94.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.94.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.95.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.95.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.95.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.96.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.96.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.96.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.97.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.97.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.97.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.98.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.98.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.98.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.99.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.99.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.experts.99.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.gate.e_score_correction_bias": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.gate.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.shared_experts.down_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.shared_experts.gate_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.mlp.shared_experts.up_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.post_attention_layernorm.weight": "model-00049-of-00092.safetensors", + "model.layers.48.self_attn.k_norm.weight": "model-00049-of-00092.safetensors", + "model.layers.48.self_attn.k_proj.bias": "model-00049-of-00092.safetensors", + "model.layers.48.self_attn.k_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.self_attn.o_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.self_attn.q_norm.weight": "model-00049-of-00092.safetensors", + "model.layers.48.self_attn.q_proj.bias": "model-00049-of-00092.safetensors", + "model.layers.48.self_attn.q_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.48.self_attn.v_proj.bias": "model-00049-of-00092.safetensors", + "model.layers.48.self_attn.v_proj.weight": "model-00049-of-00092.safetensors", + "model.layers.49.input_layernorm.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.0.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.0.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.0.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.1.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.1.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.1.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.10.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.10.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.10.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.100.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.100.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.100.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.101.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.101.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.101.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.102.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.102.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.102.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.103.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.103.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.103.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.104.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.104.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.104.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.105.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.105.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.105.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.106.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.106.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.106.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.107.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.107.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.107.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.108.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.108.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.108.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.109.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.109.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.109.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.11.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.11.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.11.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.110.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.110.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.110.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.111.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.111.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.111.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.112.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.112.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.112.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.113.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.113.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.113.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.114.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.114.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.114.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.115.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.115.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.115.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.116.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.116.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.116.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.117.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.117.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.117.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.118.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.118.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.118.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.119.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.119.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.119.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.12.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.12.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.12.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.120.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.120.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.120.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.121.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.121.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.121.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.122.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.122.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.122.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.123.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.123.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.123.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.124.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.124.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.124.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.125.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.125.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.125.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.126.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.126.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.126.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.127.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.127.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.127.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.128.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.128.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.128.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.129.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.129.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.129.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.13.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.13.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.13.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.130.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.130.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.130.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.131.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.131.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.131.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.132.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.132.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.132.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.133.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.133.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.133.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.134.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.134.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.134.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.135.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.135.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.135.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.136.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.136.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.136.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.137.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.137.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.137.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.138.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.138.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.138.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.139.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.139.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.139.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.14.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.14.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.14.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.140.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.140.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.140.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.141.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.141.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.141.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.142.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.142.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.142.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.143.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.143.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.143.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.144.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.144.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.144.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.145.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.145.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.145.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.146.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.146.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.146.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.147.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.147.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.147.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.148.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.148.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.148.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.149.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.149.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.149.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.15.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.15.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.15.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.150.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.150.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.150.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.151.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.151.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.151.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.152.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.152.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.152.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.153.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.153.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.153.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.154.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.154.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.154.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.155.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.155.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.155.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.156.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.156.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.156.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.157.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.157.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.157.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.158.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.158.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.158.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.159.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.159.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.159.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.16.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.16.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.16.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.17.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.17.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.17.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.18.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.18.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.18.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.19.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.19.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.19.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.2.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.2.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.2.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.20.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.20.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.20.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.21.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.21.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.21.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.22.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.22.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.22.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.23.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.23.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.23.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.24.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.24.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.24.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.25.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.25.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.25.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.26.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.26.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.26.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.27.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.27.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.27.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.28.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.28.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.28.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.29.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.29.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.29.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.3.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.3.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.3.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.30.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.30.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.30.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.31.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.31.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.31.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.32.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.32.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.32.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.33.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.33.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.33.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.34.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.34.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.34.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.35.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.35.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.35.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.36.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.36.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.36.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.37.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.37.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.37.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.38.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.38.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.38.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.39.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.39.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.39.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.4.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.4.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.4.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.40.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.40.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.40.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.41.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.41.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.41.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.42.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.42.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.42.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.43.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.43.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.43.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.44.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.44.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.44.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.45.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.45.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.45.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.46.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.46.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.46.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.47.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.47.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.47.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.48.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.48.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.48.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.49.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.49.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.49.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.5.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.5.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.5.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.50.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.50.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.50.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.51.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.51.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.51.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.52.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.52.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.52.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.53.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.53.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.53.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.54.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.54.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.54.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.55.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.55.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.55.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.56.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.56.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.56.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.57.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.57.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.57.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.58.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.58.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.58.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.59.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.59.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.59.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.6.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.6.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.6.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.60.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.60.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.60.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.61.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.61.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.61.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.62.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.62.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.62.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.63.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.63.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.63.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.64.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.64.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.64.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.65.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.65.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.65.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.66.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.66.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.66.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.67.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.67.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.67.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.68.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.68.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.68.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.69.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.69.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.69.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.7.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.7.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.7.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.70.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.70.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.70.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.71.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.71.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.71.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.72.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.72.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.72.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.73.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.73.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.73.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.74.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.74.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.74.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.75.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.75.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.75.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.76.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.76.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.76.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.77.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.77.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.77.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.78.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.78.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.78.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.79.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.79.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.79.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.8.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.8.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.8.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.80.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.80.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.80.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.81.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.81.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.81.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.82.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.82.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.82.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.83.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.83.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.83.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.84.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.84.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.84.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.85.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.85.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.85.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.86.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.86.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.86.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.87.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.87.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.87.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.88.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.88.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.88.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.89.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.89.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.89.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.9.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.9.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.9.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.90.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.90.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.90.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.91.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.91.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.91.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.92.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.92.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.92.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.93.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.93.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.93.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.94.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.94.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.94.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.95.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.95.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.95.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.96.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.96.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.96.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.97.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.97.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.97.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.98.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.98.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.98.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.99.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.99.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.experts.99.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.gate.e_score_correction_bias": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.gate.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.shared_experts.down_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.shared_experts.gate_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.mlp.shared_experts.up_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.post_attention_layernorm.weight": "model-00050-of-00092.safetensors", + "model.layers.49.self_attn.k_norm.weight": "model-00050-of-00092.safetensors", + "model.layers.49.self_attn.k_proj.bias": "model-00050-of-00092.safetensors", + "model.layers.49.self_attn.k_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.self_attn.o_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.self_attn.q_norm.weight": "model-00050-of-00092.safetensors", + "model.layers.49.self_attn.q_proj.bias": "model-00050-of-00092.safetensors", + "model.layers.49.self_attn.q_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.49.self_attn.v_proj.bias": "model-00050-of-00092.safetensors", + "model.layers.49.self_attn.v_proj.weight": "model-00050-of-00092.safetensors", + "model.layers.50.input_layernorm.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.0.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.0.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.0.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.1.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.1.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.1.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.10.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.10.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.10.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.100.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.100.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.100.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.101.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.101.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.101.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.102.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.102.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.102.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.103.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.103.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.103.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.104.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.104.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.104.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.105.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.105.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.105.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.106.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.106.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.106.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.107.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.107.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.107.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.108.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.108.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.108.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.109.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.109.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.109.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.11.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.11.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.11.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.110.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.110.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.110.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.111.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.111.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.111.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.112.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.112.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.112.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.113.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.113.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.113.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.114.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.114.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.114.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.115.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.115.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.115.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.116.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.116.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.116.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.117.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.117.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.117.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.118.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.118.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.118.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.119.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.119.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.119.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.12.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.12.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.12.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.120.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.120.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.120.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.121.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.121.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.121.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.122.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.122.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.122.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.123.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.123.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.123.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.124.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.124.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.124.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.125.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.125.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.125.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.126.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.126.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.126.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.127.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.127.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.127.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.128.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.128.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.128.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.129.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.129.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.129.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.13.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.13.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.13.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.130.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.130.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.130.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.131.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.131.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.131.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.132.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.132.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.132.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.133.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.133.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.133.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.134.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.134.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.134.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.135.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.135.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.135.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.136.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.136.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.136.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.137.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.137.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.137.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.138.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.138.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.138.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.139.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.139.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.139.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.14.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.14.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.14.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.140.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.140.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.140.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.141.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.141.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.141.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.142.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.142.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.142.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.143.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.143.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.143.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.144.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.144.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.144.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.145.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.145.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.145.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.146.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.146.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.146.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.147.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.147.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.147.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.148.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.148.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.148.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.149.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.149.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.149.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.15.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.15.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.15.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.150.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.150.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.150.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.151.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.151.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.151.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.152.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.152.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.152.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.153.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.153.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.153.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.154.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.154.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.154.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.155.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.155.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.155.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.156.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.156.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.156.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.157.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.157.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.157.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.158.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.158.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.158.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.159.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.159.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.159.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.16.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.16.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.16.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.17.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.17.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.17.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.18.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.18.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.18.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.19.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.19.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.19.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.2.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.2.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.2.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.20.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.20.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.20.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.21.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.21.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.21.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.22.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.22.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.22.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.23.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.23.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.23.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.24.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.24.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.24.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.25.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.25.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.25.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.26.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.26.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.26.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.27.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.27.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.27.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.28.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.28.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.28.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.29.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.29.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.29.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.3.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.3.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.3.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.30.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.30.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.30.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.31.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.31.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.31.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.32.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.32.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.32.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.33.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.33.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.33.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.34.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.34.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.34.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.35.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.35.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.35.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.36.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.36.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.36.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.37.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.37.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.37.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.38.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.38.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.38.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.39.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.39.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.39.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.4.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.4.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.4.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.40.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.40.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.40.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.41.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.41.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.41.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.42.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.42.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.42.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.43.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.43.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.43.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.44.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.44.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.44.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.45.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.45.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.45.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.46.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.46.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.46.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.47.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.47.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.47.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.48.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.48.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.48.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.49.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.49.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.49.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.5.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.5.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.5.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.50.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.50.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.50.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.51.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.51.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.51.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.52.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.52.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.52.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.53.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.53.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.53.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.54.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.54.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.54.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.55.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.55.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.55.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.56.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.56.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.56.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.57.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.57.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.57.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.58.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.58.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.58.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.59.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.59.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.59.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.6.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.6.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.6.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.60.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.60.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.60.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.61.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.61.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.61.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.62.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.62.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.62.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.63.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.63.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.63.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.64.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.64.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.64.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.65.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.65.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.65.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.66.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.66.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.66.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.67.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.67.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.67.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.68.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.68.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.68.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.69.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.69.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.69.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.7.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.7.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.7.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.70.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.70.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.70.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.71.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.71.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.71.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.72.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.72.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.72.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.73.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.73.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.73.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.74.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.74.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.74.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.75.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.75.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.75.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.76.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.76.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.76.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.77.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.77.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.77.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.78.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.78.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.78.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.79.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.79.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.79.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.8.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.8.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.8.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.80.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.80.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.80.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.81.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.81.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.81.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.82.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.82.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.82.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.83.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.83.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.83.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.84.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.84.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.84.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.85.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.85.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.85.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.86.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.86.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.86.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.87.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.87.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.87.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.88.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.88.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.88.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.89.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.89.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.89.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.9.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.9.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.9.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.90.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.90.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.90.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.91.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.91.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.91.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.92.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.92.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.92.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.93.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.93.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.93.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.94.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.94.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.94.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.95.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.95.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.95.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.96.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.96.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.96.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.97.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.97.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.97.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.98.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.98.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.98.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.99.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.99.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.experts.99.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.gate.e_score_correction_bias": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.gate.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.shared_experts.down_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.shared_experts.gate_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.mlp.shared_experts.up_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.post_attention_layernorm.weight": "model-00051-of-00092.safetensors", + "model.layers.50.self_attn.k_norm.weight": "model-00051-of-00092.safetensors", + "model.layers.50.self_attn.k_proj.bias": "model-00051-of-00092.safetensors", + "model.layers.50.self_attn.k_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.self_attn.o_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.self_attn.q_norm.weight": "model-00051-of-00092.safetensors", + "model.layers.50.self_attn.q_proj.bias": "model-00051-of-00092.safetensors", + "model.layers.50.self_attn.q_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.50.self_attn.v_proj.bias": "model-00051-of-00092.safetensors", + "model.layers.50.self_attn.v_proj.weight": "model-00051-of-00092.safetensors", + "model.layers.51.input_layernorm.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.0.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.0.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.0.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.1.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.1.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.1.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.10.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.10.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.10.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.100.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.100.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.100.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.101.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.101.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.101.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.102.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.102.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.102.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.103.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.103.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.103.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.104.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.104.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.104.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.105.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.105.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.105.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.106.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.106.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.106.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.107.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.107.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.107.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.108.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.108.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.108.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.109.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.109.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.109.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.11.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.11.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.11.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.110.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.110.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.110.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.111.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.111.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.111.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.112.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.112.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.112.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.113.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.113.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.113.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.114.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.114.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.114.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.115.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.115.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.115.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.116.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.116.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.116.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.117.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.117.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.117.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.118.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.118.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.118.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.119.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.119.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.119.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.12.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.12.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.12.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.120.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.120.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.120.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.121.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.121.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.121.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.122.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.122.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.122.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.123.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.123.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.123.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.124.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.124.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.124.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.125.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.125.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.125.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.126.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.126.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.126.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.127.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.127.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.127.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.128.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.128.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.128.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.129.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.129.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.129.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.13.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.13.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.13.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.130.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.130.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.130.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.131.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.131.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.131.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.132.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.132.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.132.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.133.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.133.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.133.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.134.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.134.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.134.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.135.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.135.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.135.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.136.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.136.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.136.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.137.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.137.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.137.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.138.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.138.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.138.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.139.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.139.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.139.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.14.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.14.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.14.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.140.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.140.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.140.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.141.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.141.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.141.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.142.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.142.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.142.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.143.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.143.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.143.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.144.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.144.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.144.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.145.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.145.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.145.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.146.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.146.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.146.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.147.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.147.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.147.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.148.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.148.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.148.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.149.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.149.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.149.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.15.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.15.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.15.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.150.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.150.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.150.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.151.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.151.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.151.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.152.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.152.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.152.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.153.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.153.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.153.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.154.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.154.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.154.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.155.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.155.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.155.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.156.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.156.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.156.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.157.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.157.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.157.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.158.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.158.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.158.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.159.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.159.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.159.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.16.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.16.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.16.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.17.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.17.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.17.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.18.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.18.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.18.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.19.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.19.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.19.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.2.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.2.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.2.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.20.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.20.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.20.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.21.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.21.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.21.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.22.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.22.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.22.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.23.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.23.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.23.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.24.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.24.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.24.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.25.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.25.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.25.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.26.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.26.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.26.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.27.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.27.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.27.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.28.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.28.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.28.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.29.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.29.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.29.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.3.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.3.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.3.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.30.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.30.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.30.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.31.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.31.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.31.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.32.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.32.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.32.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.33.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.33.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.33.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.34.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.34.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.34.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.35.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.35.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.35.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.36.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.36.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.36.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.37.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.37.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.37.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.38.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.38.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.38.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.39.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.39.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.39.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.4.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.4.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.4.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.40.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.40.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.40.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.41.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.41.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.41.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.42.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.42.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.42.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.43.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.43.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.43.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.44.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.44.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.44.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.45.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.45.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.45.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.46.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.46.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.46.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.47.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.47.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.47.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.48.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.48.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.48.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.49.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.49.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.49.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.5.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.5.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.5.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.50.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.50.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.50.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.51.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.51.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.51.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.52.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.52.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.52.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.53.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.53.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.53.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.54.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.54.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.54.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.55.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.55.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.55.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.56.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.56.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.56.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.57.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.57.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.57.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.58.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.58.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.58.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.59.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.59.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.59.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.6.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.6.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.6.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.60.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.60.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.60.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.61.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.61.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.61.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.62.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.62.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.62.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.63.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.63.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.63.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.64.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.64.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.64.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.65.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.65.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.65.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.66.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.66.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.66.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.67.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.67.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.67.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.68.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.68.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.68.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.69.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.69.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.69.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.7.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.7.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.7.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.70.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.70.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.70.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.71.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.71.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.71.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.72.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.72.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.72.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.73.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.73.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.73.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.74.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.74.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.74.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.75.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.75.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.75.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.76.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.76.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.76.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.77.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.77.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.77.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.78.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.78.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.78.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.79.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.79.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.79.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.8.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.8.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.8.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.80.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.80.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.80.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.81.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.81.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.81.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.82.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.82.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.82.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.83.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.83.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.83.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.84.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.84.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.84.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.85.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.85.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.85.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.86.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.86.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.86.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.87.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.87.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.87.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.88.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.88.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.88.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.89.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.89.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.89.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.9.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.9.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.9.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.90.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.90.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.90.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.91.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.91.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.91.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.92.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.92.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.92.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.93.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.93.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.93.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.94.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.94.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.94.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.95.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.95.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.95.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.96.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.96.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.96.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.97.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.97.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.97.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.98.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.98.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.98.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.99.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.99.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.experts.99.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.gate.e_score_correction_bias": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.gate.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.shared_experts.down_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.shared_experts.gate_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.mlp.shared_experts.up_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.post_attention_layernorm.weight": "model-00052-of-00092.safetensors", + "model.layers.51.self_attn.k_norm.weight": "model-00052-of-00092.safetensors", + "model.layers.51.self_attn.k_proj.bias": "model-00052-of-00092.safetensors", + "model.layers.51.self_attn.k_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.self_attn.o_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.self_attn.q_norm.weight": "model-00052-of-00092.safetensors", + "model.layers.51.self_attn.q_proj.bias": "model-00052-of-00092.safetensors", + "model.layers.51.self_attn.q_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.51.self_attn.v_proj.bias": "model-00052-of-00092.safetensors", + "model.layers.51.self_attn.v_proj.weight": "model-00052-of-00092.safetensors", + "model.layers.52.input_layernorm.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.0.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.0.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.0.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.1.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.1.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.1.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.10.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.10.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.10.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.100.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.100.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.100.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.101.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.101.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.101.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.102.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.102.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.102.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.103.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.103.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.103.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.104.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.104.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.104.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.105.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.105.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.105.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.106.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.106.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.106.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.107.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.107.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.107.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.108.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.108.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.108.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.109.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.109.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.109.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.11.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.11.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.11.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.110.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.110.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.110.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.111.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.111.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.111.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.112.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.112.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.112.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.113.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.113.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.113.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.114.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.114.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.114.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.115.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.115.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.115.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.116.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.116.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.116.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.117.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.117.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.117.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.118.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.118.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.118.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.119.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.119.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.119.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.12.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.12.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.12.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.120.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.120.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.120.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.121.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.121.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.121.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.122.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.122.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.122.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.123.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.123.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.123.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.124.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.124.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.124.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.125.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.125.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.125.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.126.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.126.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.126.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.127.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.127.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.127.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.128.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.128.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.128.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.129.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.129.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.129.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.13.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.13.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.13.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.130.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.130.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.130.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.131.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.131.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.131.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.132.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.132.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.132.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.133.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.133.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.133.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.134.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.134.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.134.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.135.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.135.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.135.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.136.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.136.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.136.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.137.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.137.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.137.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.138.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.138.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.138.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.139.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.139.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.139.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.14.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.14.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.14.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.140.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.140.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.140.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.141.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.141.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.141.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.142.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.142.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.142.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.143.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.143.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.143.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.144.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.144.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.144.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.145.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.145.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.145.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.146.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.146.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.146.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.147.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.147.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.147.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.148.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.148.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.148.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.149.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.149.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.149.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.15.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.15.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.15.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.150.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.150.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.150.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.151.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.151.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.151.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.152.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.152.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.152.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.153.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.153.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.153.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.154.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.154.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.154.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.155.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.155.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.155.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.156.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.156.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.156.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.157.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.157.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.157.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.158.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.158.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.158.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.159.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.159.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.159.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.16.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.16.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.16.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.17.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.17.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.17.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.18.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.18.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.18.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.19.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.19.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.19.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.2.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.2.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.2.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.20.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.20.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.20.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.21.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.21.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.21.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.22.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.22.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.22.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.23.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.23.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.23.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.24.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.24.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.24.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.25.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.25.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.25.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.26.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.26.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.26.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.27.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.27.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.27.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.28.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.28.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.28.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.29.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.29.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.29.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.3.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.3.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.3.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.30.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.30.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.30.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.31.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.31.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.31.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.32.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.32.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.32.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.33.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.33.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.33.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.34.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.34.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.34.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.35.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.35.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.35.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.36.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.36.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.36.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.37.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.37.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.37.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.38.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.38.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.38.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.39.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.39.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.39.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.4.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.4.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.4.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.40.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.40.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.40.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.41.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.41.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.41.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.42.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.42.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.42.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.43.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.43.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.43.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.44.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.44.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.44.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.45.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.45.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.45.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.46.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.46.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.46.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.47.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.47.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.47.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.48.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.48.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.48.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.49.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.49.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.49.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.5.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.5.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.5.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.50.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.50.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.50.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.51.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.51.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.51.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.52.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.52.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.52.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.53.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.53.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.53.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.54.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.54.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.54.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.55.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.55.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.55.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.56.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.56.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.56.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.57.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.57.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.57.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.58.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.58.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.58.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.59.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.59.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.59.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.6.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.6.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.6.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.60.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.60.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.60.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.61.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.61.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.61.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.62.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.62.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.62.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.63.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.63.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.63.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.64.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.64.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.64.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.65.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.65.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.65.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.66.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.66.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.66.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.67.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.67.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.67.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.68.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.68.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.68.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.69.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.69.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.69.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.7.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.7.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.7.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.70.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.70.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.70.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.71.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.71.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.71.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.72.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.72.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.72.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.73.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.73.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.73.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.74.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.74.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.74.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.75.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.75.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.75.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.76.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.76.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.76.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.77.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.77.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.77.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.78.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.78.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.78.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.79.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.79.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.79.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.8.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.8.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.8.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.80.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.80.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.80.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.81.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.81.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.81.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.82.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.82.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.82.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.83.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.83.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.83.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.84.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.84.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.84.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.85.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.85.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.85.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.86.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.86.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.86.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.87.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.87.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.87.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.88.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.88.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.88.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.89.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.89.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.89.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.9.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.9.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.9.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.90.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.90.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.90.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.91.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.91.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.91.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.92.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.92.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.92.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.93.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.93.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.93.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.94.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.94.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.94.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.95.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.95.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.95.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.96.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.96.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.96.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.97.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.97.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.97.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.98.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.98.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.98.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.99.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.99.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.experts.99.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.gate.e_score_correction_bias": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.gate.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.shared_experts.down_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.shared_experts.gate_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.mlp.shared_experts.up_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.post_attention_layernorm.weight": "model-00053-of-00092.safetensors", + "model.layers.52.self_attn.k_norm.weight": "model-00053-of-00092.safetensors", + "model.layers.52.self_attn.k_proj.bias": "model-00053-of-00092.safetensors", + "model.layers.52.self_attn.k_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.self_attn.o_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.self_attn.q_norm.weight": "model-00053-of-00092.safetensors", + "model.layers.52.self_attn.q_proj.bias": "model-00053-of-00092.safetensors", + "model.layers.52.self_attn.q_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.52.self_attn.v_proj.bias": "model-00053-of-00092.safetensors", + "model.layers.52.self_attn.v_proj.weight": "model-00053-of-00092.safetensors", + "model.layers.53.input_layernorm.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.0.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.0.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.0.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.1.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.1.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.1.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.10.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.10.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.10.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.100.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.100.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.100.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.101.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.101.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.101.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.102.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.102.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.102.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.103.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.103.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.103.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.104.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.104.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.104.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.105.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.105.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.105.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.106.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.106.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.106.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.107.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.107.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.107.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.108.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.108.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.108.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.109.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.109.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.109.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.11.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.11.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.11.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.110.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.110.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.110.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.111.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.111.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.111.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.112.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.112.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.112.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.113.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.113.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.113.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.114.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.114.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.114.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.115.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.115.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.115.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.116.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.116.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.116.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.117.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.117.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.117.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.118.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.118.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.118.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.119.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.119.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.119.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.12.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.12.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.12.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.120.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.120.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.120.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.121.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.121.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.121.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.122.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.122.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.122.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.123.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.123.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.123.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.124.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.124.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.124.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.125.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.125.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.125.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.126.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.126.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.126.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.127.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.127.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.127.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.128.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.128.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.128.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.129.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.129.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.129.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.13.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.13.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.13.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.130.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.130.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.130.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.131.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.131.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.131.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.132.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.132.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.132.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.133.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.133.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.133.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.134.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.134.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.134.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.135.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.135.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.135.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.136.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.136.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.136.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.137.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.137.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.137.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.138.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.138.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.138.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.139.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.139.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.139.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.14.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.14.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.14.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.140.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.140.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.140.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.141.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.141.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.141.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.142.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.142.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.142.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.143.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.143.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.143.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.144.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.144.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.144.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.145.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.145.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.145.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.146.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.146.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.146.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.147.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.147.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.147.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.148.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.148.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.148.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.149.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.149.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.149.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.15.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.15.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.15.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.150.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.150.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.150.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.151.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.151.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.151.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.152.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.152.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.152.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.153.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.153.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.153.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.154.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.154.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.154.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.155.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.155.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.155.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.156.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.156.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.156.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.157.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.157.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.157.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.158.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.158.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.158.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.159.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.159.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.159.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.16.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.16.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.16.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.17.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.17.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.17.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.18.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.18.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.18.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.19.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.19.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.19.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.2.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.2.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.2.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.20.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.20.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.20.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.21.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.21.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.21.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.22.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.22.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.22.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.23.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.23.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.23.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.24.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.24.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.24.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.25.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.25.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.25.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.26.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.26.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.26.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.27.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.27.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.27.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.28.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.28.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.28.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.29.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.29.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.29.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.3.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.3.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.3.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.30.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.30.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.30.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.31.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.31.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.31.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.32.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.32.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.32.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.33.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.33.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.33.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.34.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.34.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.34.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.35.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.35.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.35.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.36.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.36.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.36.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.37.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.37.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.37.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.38.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.38.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.38.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.39.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.39.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.39.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.4.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.4.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.4.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.40.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.40.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.40.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.41.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.41.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.41.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.42.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.42.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.42.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.43.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.43.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.43.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.44.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.44.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.44.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.45.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.45.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.45.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.46.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.46.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.46.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.47.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.47.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.47.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.48.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.48.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.48.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.49.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.49.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.49.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.5.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.5.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.5.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.50.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.50.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.50.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.51.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.51.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.51.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.52.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.52.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.52.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.53.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.53.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.53.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.54.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.54.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.54.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.55.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.55.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.55.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.56.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.56.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.56.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.57.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.57.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.57.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.58.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.58.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.58.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.59.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.59.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.59.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.6.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.6.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.6.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.60.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.60.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.60.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.61.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.61.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.61.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.62.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.62.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.62.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.63.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.63.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.63.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.64.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.64.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.64.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.65.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.65.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.65.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.66.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.66.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.66.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.67.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.67.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.67.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.68.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.68.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.68.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.69.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.69.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.69.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.7.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.7.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.7.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.70.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.70.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.70.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.71.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.71.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.71.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.72.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.72.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.72.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.73.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.73.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.73.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.74.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.74.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.74.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.75.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.75.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.75.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.76.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.76.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.76.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.77.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.77.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.77.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.78.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.78.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.78.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.79.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.79.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.79.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.8.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.8.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.8.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.80.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.80.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.80.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.81.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.81.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.81.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.82.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.82.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.82.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.83.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.83.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.83.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.84.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.84.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.84.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.85.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.85.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.85.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.86.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.86.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.86.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.87.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.87.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.87.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.88.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.88.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.88.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.89.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.89.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.89.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.9.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.9.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.9.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.90.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.90.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.90.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.91.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.91.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.91.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.92.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.92.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.92.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.93.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.93.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.93.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.94.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.94.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.94.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.95.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.95.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.95.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.96.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.96.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.96.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.97.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.97.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.97.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.98.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.98.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.98.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.99.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.99.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.experts.99.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.gate.e_score_correction_bias": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.gate.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.shared_experts.down_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.shared_experts.gate_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.mlp.shared_experts.up_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.post_attention_layernorm.weight": "model-00054-of-00092.safetensors", + "model.layers.53.self_attn.k_norm.weight": "model-00054-of-00092.safetensors", + "model.layers.53.self_attn.k_proj.bias": "model-00054-of-00092.safetensors", + "model.layers.53.self_attn.k_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.self_attn.o_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.self_attn.q_norm.weight": "model-00054-of-00092.safetensors", + "model.layers.53.self_attn.q_proj.bias": "model-00054-of-00092.safetensors", + "model.layers.53.self_attn.q_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.53.self_attn.v_proj.bias": "model-00054-of-00092.safetensors", + "model.layers.53.self_attn.v_proj.weight": "model-00054-of-00092.safetensors", + "model.layers.54.input_layernorm.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.0.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.0.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.0.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.1.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.1.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.1.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.10.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.10.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.10.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.100.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.100.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.100.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.101.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.101.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.101.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.102.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.102.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.102.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.103.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.103.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.103.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.104.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.104.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.104.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.105.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.105.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.105.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.106.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.106.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.106.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.107.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.107.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.107.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.108.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.108.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.108.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.109.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.109.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.109.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.11.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.11.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.11.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.110.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.110.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.110.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.111.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.111.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.111.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.112.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.112.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.112.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.113.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.113.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.113.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.114.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.114.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.114.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.115.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.115.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.115.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.116.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.116.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.116.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.117.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.117.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.117.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.118.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.118.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.118.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.119.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.119.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.119.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.12.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.12.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.12.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.120.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.120.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.120.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.121.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.121.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.121.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.122.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.122.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.122.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.123.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.123.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.123.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.124.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.124.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.124.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.125.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.125.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.125.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.126.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.126.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.126.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.127.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.127.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.127.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.128.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.128.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.128.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.129.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.129.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.129.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.13.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.13.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.13.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.130.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.130.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.130.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.131.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.131.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.131.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.132.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.132.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.132.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.133.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.133.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.133.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.134.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.134.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.134.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.135.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.135.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.135.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.136.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.136.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.136.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.137.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.137.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.137.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.138.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.138.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.138.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.139.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.139.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.139.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.14.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.14.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.14.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.140.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.140.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.140.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.141.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.141.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.141.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.142.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.142.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.142.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.143.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.143.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.143.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.144.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.144.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.144.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.145.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.145.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.145.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.146.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.146.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.146.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.147.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.147.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.147.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.148.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.148.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.148.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.149.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.149.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.149.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.15.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.15.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.15.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.150.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.150.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.150.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.151.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.151.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.151.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.152.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.152.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.152.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.153.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.153.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.153.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.154.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.154.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.154.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.155.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.155.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.155.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.156.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.156.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.156.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.157.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.157.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.157.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.158.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.158.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.158.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.159.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.159.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.159.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.16.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.16.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.16.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.17.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.17.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.17.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.18.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.18.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.18.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.19.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.19.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.19.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.2.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.2.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.2.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.20.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.20.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.20.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.21.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.21.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.21.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.22.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.22.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.22.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.23.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.23.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.23.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.24.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.24.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.24.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.25.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.25.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.25.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.26.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.26.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.26.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.27.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.27.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.27.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.28.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.28.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.28.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.29.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.29.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.29.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.3.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.3.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.3.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.30.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.30.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.30.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.31.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.31.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.31.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.32.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.32.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.32.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.33.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.33.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.33.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.34.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.34.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.34.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.35.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.35.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.35.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.36.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.36.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.36.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.37.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.37.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.37.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.38.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.38.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.38.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.39.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.39.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.39.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.4.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.4.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.4.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.40.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.40.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.40.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.41.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.41.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.41.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.42.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.42.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.42.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.43.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.43.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.43.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.44.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.44.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.44.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.45.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.45.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.45.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.46.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.46.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.46.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.47.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.47.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.47.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.48.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.48.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.48.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.49.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.49.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.49.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.5.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.5.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.5.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.50.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.50.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.50.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.51.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.51.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.51.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.52.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.52.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.52.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.53.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.53.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.53.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.54.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.54.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.54.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.55.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.55.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.55.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.56.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.56.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.56.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.57.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.57.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.57.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.58.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.58.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.58.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.59.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.59.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.59.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.6.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.6.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.6.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.60.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.60.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.60.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.61.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.61.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.61.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.62.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.62.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.62.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.63.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.63.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.63.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.64.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.64.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.64.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.65.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.65.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.65.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.66.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.66.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.66.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.67.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.67.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.67.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.68.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.68.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.68.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.69.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.69.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.69.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.7.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.7.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.7.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.70.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.70.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.70.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.71.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.71.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.71.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.72.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.72.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.72.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.73.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.73.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.73.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.74.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.74.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.74.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.75.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.75.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.75.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.76.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.76.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.76.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.77.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.77.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.77.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.78.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.78.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.78.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.79.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.79.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.79.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.8.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.8.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.8.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.80.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.80.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.80.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.81.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.81.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.81.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.82.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.82.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.82.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.83.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.83.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.83.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.84.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.84.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.84.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.85.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.85.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.85.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.86.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.86.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.86.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.87.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.87.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.87.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.88.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.88.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.88.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.89.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.89.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.89.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.9.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.9.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.9.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.90.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.90.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.90.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.91.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.91.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.91.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.92.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.92.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.92.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.93.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.93.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.93.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.94.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.94.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.94.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.95.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.95.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.95.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.96.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.96.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.96.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.97.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.97.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.97.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.98.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.98.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.98.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.99.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.99.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.experts.99.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.gate.e_score_correction_bias": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.gate.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.shared_experts.down_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.shared_experts.gate_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.mlp.shared_experts.up_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.post_attention_layernorm.weight": "model-00055-of-00092.safetensors", + "model.layers.54.self_attn.k_norm.weight": "model-00055-of-00092.safetensors", + "model.layers.54.self_attn.k_proj.bias": "model-00055-of-00092.safetensors", + "model.layers.54.self_attn.k_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.self_attn.o_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.self_attn.q_norm.weight": "model-00055-of-00092.safetensors", + "model.layers.54.self_attn.q_proj.bias": "model-00055-of-00092.safetensors", + "model.layers.54.self_attn.q_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.54.self_attn.v_proj.bias": "model-00055-of-00092.safetensors", + "model.layers.54.self_attn.v_proj.weight": "model-00055-of-00092.safetensors", + "model.layers.55.input_layernorm.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.0.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.0.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.0.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.1.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.1.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.1.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.10.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.10.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.10.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.100.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.100.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.100.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.101.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.101.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.101.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.102.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.102.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.102.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.103.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.103.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.103.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.104.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.104.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.104.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.105.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.105.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.105.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.106.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.106.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.106.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.107.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.107.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.107.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.108.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.108.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.108.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.109.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.109.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.109.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.11.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.11.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.11.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.110.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.110.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.110.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.111.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.111.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.111.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.112.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.112.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.112.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.113.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.113.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.113.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.114.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.114.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.114.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.115.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.115.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.115.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.116.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.116.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.116.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.117.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.117.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.117.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.118.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.118.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.118.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.119.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.119.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.119.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.12.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.12.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.12.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.120.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.120.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.120.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.121.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.121.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.121.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.122.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.122.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.122.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.123.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.123.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.123.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.124.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.124.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.124.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.125.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.125.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.125.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.126.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.126.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.126.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.127.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.127.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.127.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.128.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.128.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.128.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.129.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.129.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.129.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.13.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.13.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.13.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.130.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.130.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.130.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.131.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.131.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.131.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.132.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.132.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.132.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.133.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.133.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.133.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.134.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.134.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.134.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.135.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.135.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.135.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.136.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.136.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.136.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.137.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.137.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.137.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.138.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.138.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.138.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.139.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.139.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.139.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.14.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.14.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.14.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.140.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.140.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.140.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.141.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.141.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.141.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.142.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.142.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.142.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.143.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.143.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.143.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.144.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.144.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.144.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.145.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.145.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.145.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.146.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.146.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.146.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.147.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.147.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.147.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.148.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.148.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.148.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.149.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.149.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.149.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.15.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.15.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.15.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.150.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.150.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.150.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.151.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.151.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.151.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.152.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.152.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.152.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.153.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.153.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.153.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.154.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.154.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.154.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.155.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.155.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.155.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.156.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.156.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.156.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.157.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.157.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.157.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.158.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.158.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.158.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.159.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.159.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.159.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.16.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.16.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.16.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.17.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.17.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.17.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.18.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.18.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.18.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.19.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.19.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.19.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.2.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.2.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.2.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.20.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.20.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.20.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.21.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.21.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.21.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.22.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.22.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.22.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.23.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.23.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.23.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.24.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.24.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.24.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.25.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.25.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.25.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.26.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.26.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.26.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.27.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.27.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.27.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.28.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.28.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.28.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.29.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.29.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.29.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.3.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.3.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.3.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.30.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.30.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.30.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.31.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.31.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.31.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.32.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.32.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.32.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.33.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.33.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.33.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.34.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.34.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.34.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.35.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.35.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.35.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.36.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.36.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.36.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.37.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.37.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.37.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.38.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.38.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.38.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.39.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.39.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.39.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.4.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.4.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.4.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.40.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.40.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.40.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.41.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.41.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.41.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.42.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.42.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.42.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.43.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.43.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.43.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.44.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.44.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.44.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.45.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.45.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.45.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.46.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.46.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.46.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.47.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.47.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.47.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.48.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.48.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.48.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.49.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.49.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.49.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.5.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.5.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.5.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.50.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.50.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.50.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.51.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.51.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.51.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.52.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.52.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.52.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.53.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.53.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.53.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.54.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.54.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.54.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.55.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.55.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.55.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.56.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.56.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.56.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.57.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.57.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.57.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.58.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.58.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.58.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.59.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.59.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.59.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.6.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.6.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.6.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.60.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.60.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.60.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.61.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.61.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.61.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.62.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.62.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.62.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.63.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.63.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.63.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.64.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.64.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.64.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.65.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.65.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.65.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.66.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.66.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.66.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.67.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.67.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.67.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.68.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.68.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.68.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.69.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.69.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.69.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.7.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.7.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.7.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.70.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.70.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.70.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.71.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.71.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.71.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.72.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.72.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.72.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.73.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.73.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.73.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.74.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.74.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.74.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.75.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.75.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.75.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.76.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.76.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.76.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.77.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.77.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.77.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.78.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.78.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.78.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.79.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.79.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.79.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.8.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.8.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.8.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.80.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.80.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.80.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.81.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.81.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.81.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.82.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.82.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.82.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.83.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.83.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.83.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.84.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.84.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.84.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.85.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.85.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.85.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.86.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.86.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.86.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.87.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.87.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.87.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.88.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.88.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.88.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.89.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.89.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.89.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.9.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.9.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.9.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.90.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.90.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.90.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.91.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.91.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.91.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.92.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.92.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.92.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.93.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.93.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.93.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.94.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.94.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.94.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.95.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.95.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.95.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.96.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.96.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.96.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.97.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.97.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.97.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.98.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.98.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.98.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.99.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.99.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.experts.99.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.gate.e_score_correction_bias": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.gate.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.shared_experts.down_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.shared_experts.gate_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.mlp.shared_experts.up_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.post_attention_layernorm.weight": "model-00056-of-00092.safetensors", + "model.layers.55.self_attn.k_norm.weight": "model-00056-of-00092.safetensors", + "model.layers.55.self_attn.k_proj.bias": "model-00056-of-00092.safetensors", + "model.layers.55.self_attn.k_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.self_attn.o_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.self_attn.q_norm.weight": "model-00056-of-00092.safetensors", + "model.layers.55.self_attn.q_proj.bias": "model-00056-of-00092.safetensors", + "model.layers.55.self_attn.q_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.55.self_attn.v_proj.bias": "model-00056-of-00092.safetensors", + "model.layers.55.self_attn.v_proj.weight": "model-00056-of-00092.safetensors", + "model.layers.56.input_layernorm.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.0.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.0.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.0.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.1.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.1.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.1.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.10.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.10.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.10.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.100.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.100.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.100.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.101.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.101.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.101.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.102.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.102.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.102.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.103.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.103.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.103.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.104.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.104.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.104.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.105.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.105.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.105.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.106.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.106.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.106.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.107.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.107.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.107.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.108.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.108.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.108.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.109.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.109.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.109.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.11.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.11.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.11.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.110.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.110.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.110.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.111.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.111.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.111.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.112.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.112.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.112.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.113.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.113.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.113.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.114.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.114.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.114.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.115.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.115.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.115.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.116.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.116.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.116.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.117.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.117.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.117.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.118.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.118.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.118.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.119.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.119.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.119.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.12.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.12.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.12.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.120.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.120.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.120.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.121.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.121.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.121.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.122.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.122.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.122.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.123.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.123.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.123.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.124.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.124.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.124.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.125.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.125.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.125.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.126.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.126.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.126.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.127.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.127.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.127.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.128.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.128.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.128.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.129.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.129.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.129.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.13.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.13.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.13.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.130.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.130.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.130.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.131.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.131.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.131.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.132.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.132.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.132.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.133.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.133.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.133.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.134.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.134.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.134.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.135.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.135.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.135.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.136.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.136.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.136.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.137.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.137.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.137.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.138.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.138.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.138.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.139.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.139.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.139.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.14.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.14.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.14.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.140.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.140.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.140.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.141.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.141.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.141.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.142.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.142.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.142.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.143.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.143.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.143.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.144.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.144.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.144.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.145.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.145.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.145.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.146.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.146.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.146.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.147.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.147.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.147.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.148.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.148.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.148.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.149.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.149.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.149.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.15.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.15.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.15.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.150.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.150.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.150.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.151.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.151.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.151.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.152.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.152.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.152.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.153.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.153.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.153.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.154.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.154.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.154.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.155.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.155.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.155.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.156.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.156.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.156.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.157.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.157.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.157.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.158.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.158.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.158.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.159.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.159.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.159.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.16.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.16.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.16.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.17.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.17.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.17.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.18.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.18.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.18.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.19.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.19.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.19.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.2.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.2.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.2.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.20.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.20.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.20.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.21.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.21.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.21.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.22.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.22.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.22.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.23.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.23.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.23.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.24.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.24.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.24.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.25.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.25.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.25.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.26.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.26.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.26.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.27.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.27.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.27.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.28.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.28.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.28.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.29.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.29.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.29.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.3.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.3.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.3.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.30.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.30.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.30.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.31.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.31.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.31.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.32.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.32.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.32.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.33.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.33.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.33.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.34.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.34.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.34.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.35.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.35.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.35.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.36.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.36.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.36.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.37.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.37.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.37.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.38.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.38.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.38.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.39.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.39.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.39.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.4.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.4.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.4.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.40.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.40.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.40.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.41.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.41.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.41.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.42.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.42.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.42.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.43.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.43.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.43.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.44.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.44.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.44.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.45.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.45.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.45.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.46.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.46.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.46.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.47.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.47.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.47.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.48.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.48.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.48.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.49.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.49.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.49.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.5.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.5.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.5.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.50.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.50.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.50.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.51.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.51.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.51.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.52.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.52.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.52.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.53.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.53.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.53.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.54.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.54.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.54.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.55.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.55.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.55.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.56.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.56.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.56.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.57.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.57.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.57.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.58.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.58.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.58.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.59.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.59.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.59.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.6.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.6.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.6.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.60.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.60.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.60.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.61.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.61.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.61.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.62.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.62.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.62.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.63.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.63.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.63.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.64.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.64.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.64.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.65.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.65.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.65.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.66.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.66.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.66.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.67.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.67.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.67.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.68.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.68.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.68.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.69.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.69.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.69.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.7.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.7.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.7.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.70.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.70.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.70.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.71.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.71.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.71.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.72.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.72.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.72.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.73.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.73.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.73.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.74.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.74.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.74.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.75.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.75.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.75.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.76.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.76.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.76.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.77.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.77.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.77.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.78.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.78.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.78.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.79.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.79.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.79.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.8.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.8.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.8.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.80.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.80.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.80.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.81.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.81.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.81.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.82.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.82.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.82.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.83.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.83.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.83.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.84.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.84.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.84.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.85.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.85.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.85.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.86.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.86.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.86.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.87.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.87.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.87.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.88.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.88.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.88.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.89.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.89.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.89.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.9.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.9.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.9.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.90.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.90.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.90.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.91.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.91.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.91.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.92.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.92.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.92.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.93.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.93.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.93.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.94.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.94.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.94.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.95.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.95.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.95.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.96.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.96.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.96.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.97.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.97.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.97.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.98.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.98.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.98.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.99.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.99.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.experts.99.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.gate.e_score_correction_bias": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.gate.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.shared_experts.down_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.shared_experts.gate_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.mlp.shared_experts.up_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.post_attention_layernorm.weight": "model-00057-of-00092.safetensors", + "model.layers.56.self_attn.k_norm.weight": "model-00057-of-00092.safetensors", + "model.layers.56.self_attn.k_proj.bias": "model-00057-of-00092.safetensors", + "model.layers.56.self_attn.k_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.self_attn.o_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.self_attn.q_norm.weight": "model-00057-of-00092.safetensors", + "model.layers.56.self_attn.q_proj.bias": "model-00057-of-00092.safetensors", + "model.layers.56.self_attn.q_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.56.self_attn.v_proj.bias": "model-00057-of-00092.safetensors", + "model.layers.56.self_attn.v_proj.weight": "model-00057-of-00092.safetensors", + "model.layers.57.input_layernorm.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.0.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.0.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.0.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.1.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.1.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.1.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.10.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.10.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.10.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.100.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.100.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.100.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.101.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.101.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.101.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.102.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.102.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.102.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.103.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.103.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.103.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.104.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.104.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.104.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.105.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.105.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.105.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.106.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.106.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.106.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.107.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.107.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.107.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.108.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.108.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.108.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.109.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.109.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.109.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.11.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.11.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.11.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.110.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.110.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.110.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.111.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.111.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.111.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.112.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.112.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.112.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.113.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.113.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.113.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.114.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.114.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.114.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.115.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.115.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.115.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.116.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.116.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.116.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.117.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.117.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.117.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.118.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.118.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.118.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.119.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.119.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.119.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.12.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.12.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.12.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.120.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.120.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.120.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.121.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.121.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.121.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.122.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.122.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.122.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.123.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.123.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.123.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.124.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.124.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.124.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.125.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.125.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.125.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.126.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.126.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.126.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.127.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.127.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.127.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.128.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.128.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.128.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.129.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.129.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.129.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.13.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.13.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.13.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.130.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.130.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.130.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.131.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.131.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.131.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.132.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.132.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.132.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.133.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.133.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.133.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.134.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.134.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.134.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.135.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.135.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.135.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.136.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.136.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.136.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.137.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.137.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.137.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.138.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.138.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.138.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.139.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.139.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.139.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.14.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.14.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.14.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.140.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.140.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.140.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.141.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.141.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.141.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.142.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.142.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.142.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.143.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.143.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.143.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.144.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.144.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.144.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.145.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.145.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.145.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.146.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.146.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.146.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.147.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.147.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.147.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.148.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.148.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.148.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.149.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.149.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.149.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.15.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.15.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.15.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.150.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.150.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.150.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.151.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.151.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.151.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.152.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.152.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.152.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.153.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.153.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.153.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.154.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.154.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.154.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.155.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.155.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.155.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.156.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.156.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.156.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.157.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.157.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.157.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.158.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.158.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.158.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.159.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.159.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.159.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.16.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.16.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.16.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.17.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.17.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.17.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.18.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.18.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.18.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.19.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.19.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.19.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.2.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.2.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.2.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.20.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.20.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.20.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.21.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.21.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.21.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.22.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.22.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.22.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.23.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.23.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.23.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.24.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.24.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.24.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.25.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.25.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.25.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.26.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.26.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.26.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.27.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.27.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.27.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.28.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.28.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.28.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.29.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.29.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.29.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.3.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.3.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.3.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.30.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.30.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.30.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.31.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.31.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.31.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.32.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.32.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.32.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.33.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.33.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.33.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.34.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.34.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.34.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.35.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.35.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.35.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.36.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.36.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.36.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.37.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.37.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.37.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.38.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.38.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.38.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.39.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.39.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.39.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.4.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.4.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.4.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.40.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.40.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.40.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.41.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.41.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.41.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.42.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.42.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.42.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.43.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.43.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.43.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.44.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.44.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.44.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.45.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.45.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.45.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.46.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.46.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.46.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.47.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.47.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.47.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.48.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.48.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.48.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.49.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.49.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.49.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.5.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.5.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.5.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.50.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.50.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.50.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.51.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.51.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.51.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.52.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.52.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.52.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.53.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.53.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.53.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.54.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.54.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.54.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.55.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.55.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.55.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.56.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.56.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.56.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.57.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.57.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.57.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.58.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.58.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.58.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.59.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.59.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.59.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.6.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.6.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.6.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.60.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.60.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.60.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.61.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.61.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.61.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.62.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.62.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.62.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.63.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.63.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.63.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.64.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.64.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.64.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.65.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.65.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.65.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.66.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.66.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.66.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.67.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.67.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.67.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.68.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.68.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.68.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.69.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.69.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.69.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.7.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.7.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.7.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.70.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.70.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.70.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.71.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.71.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.71.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.72.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.72.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.72.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.73.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.73.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.73.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.74.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.74.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.74.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.75.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.75.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.75.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.76.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.76.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.76.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.77.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.77.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.77.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.78.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.78.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.78.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.79.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.79.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.79.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.8.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.8.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.8.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.80.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.80.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.80.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.81.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.81.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.81.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.82.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.82.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.82.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.83.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.83.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.83.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.84.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.84.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.84.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.85.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.85.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.85.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.86.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.86.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.86.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.87.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.87.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.87.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.88.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.88.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.88.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.89.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.89.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.89.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.9.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.9.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.9.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.90.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.90.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.90.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.91.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.91.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.91.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.92.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.92.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.92.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.93.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.93.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.93.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.94.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.94.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.94.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.95.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.95.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.95.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.96.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.96.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.96.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.97.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.97.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.97.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.98.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.98.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.98.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.99.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.99.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.experts.99.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.gate.e_score_correction_bias": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.gate.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.shared_experts.down_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.shared_experts.gate_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.mlp.shared_experts.up_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.post_attention_layernorm.weight": "model-00058-of-00092.safetensors", + "model.layers.57.self_attn.k_norm.weight": "model-00058-of-00092.safetensors", + "model.layers.57.self_attn.k_proj.bias": "model-00058-of-00092.safetensors", + "model.layers.57.self_attn.k_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.self_attn.o_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.self_attn.q_norm.weight": "model-00058-of-00092.safetensors", + "model.layers.57.self_attn.q_proj.bias": "model-00058-of-00092.safetensors", + "model.layers.57.self_attn.q_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.57.self_attn.v_proj.bias": "model-00058-of-00092.safetensors", + "model.layers.57.self_attn.v_proj.weight": "model-00058-of-00092.safetensors", + "model.layers.58.input_layernorm.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.0.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.0.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.0.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.1.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.1.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.1.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.10.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.10.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.10.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.100.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.100.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.100.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.101.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.101.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.101.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.102.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.102.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.102.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.103.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.103.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.103.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.104.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.104.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.104.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.105.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.105.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.105.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.106.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.106.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.106.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.107.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.107.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.107.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.108.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.108.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.108.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.109.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.109.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.109.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.11.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.11.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.11.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.110.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.110.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.110.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.111.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.111.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.111.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.112.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.112.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.112.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.113.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.113.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.113.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.114.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.114.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.114.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.115.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.115.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.115.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.116.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.116.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.116.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.117.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.117.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.117.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.118.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.118.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.118.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.119.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.119.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.119.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.12.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.12.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.12.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.120.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.120.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.120.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.121.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.121.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.121.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.122.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.122.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.122.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.123.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.123.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.123.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.124.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.124.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.124.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.125.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.125.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.125.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.126.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.126.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.126.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.127.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.127.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.127.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.128.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.128.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.128.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.129.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.129.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.129.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.13.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.13.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.13.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.130.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.130.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.130.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.131.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.131.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.131.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.132.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.132.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.132.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.133.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.133.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.133.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.134.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.134.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.134.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.135.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.135.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.135.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.136.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.136.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.136.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.137.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.137.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.137.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.138.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.138.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.138.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.139.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.139.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.139.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.14.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.14.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.14.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.140.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.140.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.140.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.141.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.141.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.141.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.142.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.142.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.142.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.143.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.143.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.143.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.144.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.144.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.144.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.145.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.145.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.145.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.146.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.146.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.146.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.147.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.147.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.147.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.148.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.148.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.148.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.149.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.149.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.149.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.15.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.15.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.15.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.150.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.150.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.150.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.151.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.151.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.151.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.152.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.152.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.152.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.153.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.153.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.153.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.154.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.154.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.154.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.155.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.155.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.155.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.156.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.156.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.156.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.157.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.157.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.157.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.158.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.158.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.158.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.159.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.159.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.159.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.16.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.16.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.16.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.17.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.17.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.17.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.18.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.18.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.18.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.19.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.19.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.19.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.2.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.2.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.2.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.20.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.20.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.20.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.21.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.21.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.21.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.22.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.22.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.22.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.23.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.23.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.23.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.24.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.24.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.24.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.25.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.25.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.25.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.26.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.26.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.26.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.27.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.27.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.27.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.28.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.28.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.28.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.29.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.29.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.29.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.3.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.3.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.3.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.30.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.30.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.30.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.31.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.31.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.31.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.32.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.32.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.32.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.33.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.33.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.33.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.34.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.34.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.34.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.35.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.35.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.35.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.36.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.36.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.36.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.37.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.37.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.37.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.38.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.38.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.38.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.39.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.39.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.39.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.4.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.4.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.4.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.40.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.40.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.40.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.41.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.41.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.41.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.42.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.42.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.42.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.43.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.43.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.43.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.44.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.44.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.44.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.45.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.45.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.45.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.46.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.46.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.46.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.47.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.47.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.47.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.48.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.48.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.48.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.49.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.49.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.49.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.5.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.5.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.5.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.50.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.50.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.50.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.51.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.51.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.51.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.52.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.52.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.52.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.53.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.53.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.53.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.54.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.54.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.54.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.55.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.55.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.55.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.56.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.56.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.56.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.57.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.57.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.57.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.58.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.58.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.58.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.59.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.59.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.59.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.6.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.6.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.6.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.60.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.60.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.60.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.61.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.61.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.61.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.62.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.62.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.62.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.63.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.63.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.63.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.64.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.64.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.64.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.65.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.65.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.65.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.66.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.66.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.66.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.67.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.67.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.67.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.68.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.68.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.68.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.69.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.69.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.69.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.7.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.7.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.7.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.70.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.70.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.70.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.71.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.71.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.71.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.72.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.72.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.72.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.73.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.73.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.73.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.74.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.74.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.74.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.75.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.75.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.75.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.76.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.76.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.76.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.77.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.77.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.77.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.78.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.78.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.78.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.79.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.79.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.79.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.8.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.8.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.8.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.80.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.80.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.80.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.81.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.81.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.81.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.82.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.82.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.82.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.83.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.83.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.83.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.84.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.84.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.84.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.85.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.85.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.85.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.86.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.86.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.86.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.87.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.87.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.87.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.88.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.88.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.88.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.89.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.89.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.89.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.9.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.9.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.9.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.90.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.90.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.90.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.91.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.91.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.91.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.92.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.92.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.92.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.93.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.93.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.93.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.94.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.94.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.94.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.95.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.95.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.95.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.96.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.96.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.96.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.97.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.97.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.97.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.98.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.98.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.98.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.99.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.99.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.experts.99.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.gate.e_score_correction_bias": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.gate.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.shared_experts.down_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.shared_experts.gate_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.mlp.shared_experts.up_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.post_attention_layernorm.weight": "model-00059-of-00092.safetensors", + "model.layers.58.self_attn.k_norm.weight": "model-00059-of-00092.safetensors", + "model.layers.58.self_attn.k_proj.bias": "model-00059-of-00092.safetensors", + "model.layers.58.self_attn.k_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.self_attn.o_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.self_attn.q_norm.weight": "model-00059-of-00092.safetensors", + "model.layers.58.self_attn.q_proj.bias": "model-00059-of-00092.safetensors", + "model.layers.58.self_attn.q_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.58.self_attn.v_proj.bias": "model-00059-of-00092.safetensors", + "model.layers.58.self_attn.v_proj.weight": "model-00059-of-00092.safetensors", + "model.layers.59.input_layernorm.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.0.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.0.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.0.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.1.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.1.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.1.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.10.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.10.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.10.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.100.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.100.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.100.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.101.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.101.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.101.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.102.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.102.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.102.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.103.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.103.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.103.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.104.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.104.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.104.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.105.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.105.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.105.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.106.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.106.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.106.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.107.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.107.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.107.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.108.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.108.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.108.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.109.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.109.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.109.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.11.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.11.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.11.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.110.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.110.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.110.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.111.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.111.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.111.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.112.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.112.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.112.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.113.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.113.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.113.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.114.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.114.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.114.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.115.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.115.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.115.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.116.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.116.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.116.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.117.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.117.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.117.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.118.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.118.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.118.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.119.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.119.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.119.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.12.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.12.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.12.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.120.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.120.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.120.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.121.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.121.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.121.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.122.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.122.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.122.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.123.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.123.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.123.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.124.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.124.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.124.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.125.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.125.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.125.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.126.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.126.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.126.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.127.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.127.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.127.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.128.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.128.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.128.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.129.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.129.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.129.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.13.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.13.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.13.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.130.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.130.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.130.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.131.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.131.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.131.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.132.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.132.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.132.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.133.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.133.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.133.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.134.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.134.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.134.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.135.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.135.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.135.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.136.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.136.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.136.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.137.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.137.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.137.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.138.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.138.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.138.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.139.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.139.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.139.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.14.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.14.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.14.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.140.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.140.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.140.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.141.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.141.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.141.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.142.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.142.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.142.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.143.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.143.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.143.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.144.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.144.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.144.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.145.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.145.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.145.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.146.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.146.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.146.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.147.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.147.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.147.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.148.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.148.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.148.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.149.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.149.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.149.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.15.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.15.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.15.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.150.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.150.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.150.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.151.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.151.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.151.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.152.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.152.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.152.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.153.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.153.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.153.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.154.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.154.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.154.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.155.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.155.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.155.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.156.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.156.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.156.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.157.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.157.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.157.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.158.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.158.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.158.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.159.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.159.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.159.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.16.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.16.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.16.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.17.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.17.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.17.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.18.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.18.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.18.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.19.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.19.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.19.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.2.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.2.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.2.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.20.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.20.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.20.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.21.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.21.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.21.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.22.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.22.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.22.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.23.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.23.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.23.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.24.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.24.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.24.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.25.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.25.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.25.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.26.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.26.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.26.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.27.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.27.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.27.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.28.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.28.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.28.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.29.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.29.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.29.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.3.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.3.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.3.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.30.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.30.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.30.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.31.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.31.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.31.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.32.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.32.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.32.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.33.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.33.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.33.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.34.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.34.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.34.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.35.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.35.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.35.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.36.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.36.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.36.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.37.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.37.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.37.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.38.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.38.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.38.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.39.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.39.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.39.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.4.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.4.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.4.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.40.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.40.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.40.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.41.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.41.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.41.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.42.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.42.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.42.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.43.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.43.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.43.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.44.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.44.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.44.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.45.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.45.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.45.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.46.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.46.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.46.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.47.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.47.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.47.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.48.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.48.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.48.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.49.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.49.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.49.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.5.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.5.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.5.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.50.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.50.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.50.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.51.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.51.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.51.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.52.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.52.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.52.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.53.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.53.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.53.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.54.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.54.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.54.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.55.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.55.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.55.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.56.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.56.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.56.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.57.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.57.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.57.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.58.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.58.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.58.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.59.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.59.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.59.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.6.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.6.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.6.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.60.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.60.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.60.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.61.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.61.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.61.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.62.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.62.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.62.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.63.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.63.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.63.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.64.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.64.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.64.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.65.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.65.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.65.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.66.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.66.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.66.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.67.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.67.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.67.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.68.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.68.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.68.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.69.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.69.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.69.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.7.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.7.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.7.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.70.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.70.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.70.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.71.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.71.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.71.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.72.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.72.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.72.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.73.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.73.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.73.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.74.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.74.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.74.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.75.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.75.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.75.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.76.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.76.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.76.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.77.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.77.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.77.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.78.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.78.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.78.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.79.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.79.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.79.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.8.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.8.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.8.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.80.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.80.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.80.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.81.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.81.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.81.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.82.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.82.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.82.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.83.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.83.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.83.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.84.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.84.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.84.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.85.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.85.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.85.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.86.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.86.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.86.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.87.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.87.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.87.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.88.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.88.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.88.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.89.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.89.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.89.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.9.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.9.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.9.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.90.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.90.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.90.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.91.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.91.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.91.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.92.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.92.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.92.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.93.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.93.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.93.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.94.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.94.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.94.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.95.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.95.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.95.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.96.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.96.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.96.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.97.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.97.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.97.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.98.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.98.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.98.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.99.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.99.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.experts.99.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.gate.e_score_correction_bias": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.gate.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.shared_experts.down_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.shared_experts.gate_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.mlp.shared_experts.up_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.post_attention_layernorm.weight": "model-00060-of-00092.safetensors", + "model.layers.59.self_attn.k_norm.weight": "model-00060-of-00092.safetensors", + "model.layers.59.self_attn.k_proj.bias": "model-00060-of-00092.safetensors", + "model.layers.59.self_attn.k_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.self_attn.o_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.self_attn.q_norm.weight": "model-00060-of-00092.safetensors", + "model.layers.59.self_attn.q_proj.bias": "model-00060-of-00092.safetensors", + "model.layers.59.self_attn.q_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.59.self_attn.v_proj.bias": "model-00060-of-00092.safetensors", + "model.layers.59.self_attn.v_proj.weight": "model-00060-of-00092.safetensors", + "model.layers.60.input_layernorm.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.0.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.0.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.0.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.1.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.1.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.1.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.10.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.10.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.10.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.100.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.100.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.100.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.101.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.101.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.101.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.102.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.102.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.102.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.103.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.103.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.103.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.104.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.104.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.104.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.105.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.105.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.105.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.106.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.106.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.106.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.107.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.107.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.107.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.108.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.108.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.108.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.109.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.109.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.109.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.11.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.11.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.11.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.110.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.110.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.110.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.111.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.111.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.111.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.112.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.112.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.112.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.113.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.113.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.113.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.114.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.114.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.114.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.115.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.115.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.115.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.116.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.116.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.116.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.117.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.117.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.117.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.118.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.118.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.118.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.119.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.119.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.119.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.12.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.12.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.12.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.120.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.120.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.120.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.121.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.121.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.121.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.122.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.122.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.122.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.123.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.123.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.123.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.124.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.124.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.124.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.125.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.125.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.125.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.126.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.126.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.126.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.127.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.127.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.127.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.128.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.128.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.128.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.129.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.129.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.129.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.13.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.13.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.13.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.130.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.130.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.130.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.131.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.131.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.131.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.132.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.132.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.132.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.133.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.133.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.133.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.134.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.134.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.134.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.135.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.135.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.135.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.136.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.136.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.136.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.137.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.137.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.137.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.138.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.138.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.138.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.139.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.139.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.139.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.14.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.14.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.14.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.140.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.140.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.140.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.141.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.141.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.141.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.142.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.142.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.142.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.143.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.143.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.143.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.144.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.144.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.144.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.145.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.145.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.145.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.146.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.146.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.146.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.147.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.147.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.147.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.148.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.148.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.148.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.149.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.149.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.149.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.15.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.15.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.15.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.150.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.150.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.150.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.151.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.151.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.151.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.152.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.152.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.152.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.153.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.153.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.153.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.154.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.154.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.154.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.155.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.155.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.155.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.156.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.156.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.156.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.157.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.157.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.157.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.158.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.158.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.158.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.159.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.159.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.159.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.16.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.16.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.16.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.17.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.17.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.17.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.18.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.18.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.18.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.19.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.19.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.19.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.2.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.2.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.2.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.20.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.20.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.20.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.21.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.21.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.21.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.22.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.22.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.22.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.23.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.23.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.23.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.24.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.24.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.24.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.25.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.25.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.25.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.26.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.26.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.26.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.27.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.27.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.27.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.28.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.28.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.28.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.29.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.29.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.29.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.3.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.3.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.3.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.30.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.30.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.30.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.31.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.31.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.31.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.32.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.32.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.32.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.33.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.33.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.33.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.34.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.34.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.34.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.35.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.35.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.35.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.36.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.36.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.36.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.37.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.37.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.37.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.38.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.38.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.38.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.39.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.39.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.39.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.4.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.4.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.4.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.40.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.40.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.40.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.41.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.41.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.41.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.42.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.42.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.42.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.43.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.43.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.43.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.44.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.44.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.44.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.45.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.45.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.45.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.46.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.46.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.46.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.47.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.47.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.47.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.48.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.48.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.48.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.49.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.49.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.49.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.5.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.5.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.5.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.50.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.50.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.50.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.51.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.51.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.51.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.52.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.52.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.52.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.53.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.53.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.53.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.54.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.54.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.54.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.55.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.55.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.55.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.56.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.56.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.56.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.57.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.57.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.57.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.58.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.58.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.58.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.59.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.59.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.59.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.6.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.6.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.6.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.60.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.60.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.60.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.61.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.61.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.61.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.62.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.62.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.62.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.63.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.63.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.63.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.64.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.64.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.64.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.65.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.65.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.65.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.66.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.66.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.66.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.67.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.67.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.67.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.68.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.68.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.68.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.69.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.69.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.69.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.7.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.7.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.7.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.70.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.70.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.70.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.71.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.71.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.71.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.72.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.72.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.72.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.73.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.73.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.73.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.74.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.74.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.74.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.75.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.75.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.75.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.76.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.76.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.76.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.77.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.77.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.77.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.78.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.78.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.78.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.79.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.79.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.79.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.8.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.8.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.8.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.80.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.80.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.80.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.81.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.81.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.81.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.82.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.82.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.82.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.83.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.83.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.83.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.84.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.84.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.84.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.85.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.85.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.85.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.86.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.86.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.86.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.87.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.87.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.87.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.88.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.88.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.88.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.89.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.89.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.89.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.9.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.9.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.9.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.90.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.90.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.90.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.91.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.91.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.91.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.92.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.92.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.92.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.93.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.93.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.93.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.94.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.94.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.94.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.95.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.95.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.95.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.96.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.96.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.96.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.97.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.97.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.97.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.98.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.98.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.98.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.99.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.99.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.experts.99.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.gate.e_score_correction_bias": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.gate.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.shared_experts.down_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.shared_experts.gate_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.mlp.shared_experts.up_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.post_attention_layernorm.weight": "model-00061-of-00092.safetensors", + "model.layers.60.self_attn.k_norm.weight": "model-00061-of-00092.safetensors", + "model.layers.60.self_attn.k_proj.bias": "model-00061-of-00092.safetensors", + "model.layers.60.self_attn.k_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.self_attn.o_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.self_attn.q_norm.weight": "model-00061-of-00092.safetensors", + "model.layers.60.self_attn.q_proj.bias": "model-00061-of-00092.safetensors", + "model.layers.60.self_attn.q_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.60.self_attn.v_proj.bias": "model-00061-of-00092.safetensors", + "model.layers.60.self_attn.v_proj.weight": "model-00061-of-00092.safetensors", + "model.layers.61.input_layernorm.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.0.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.0.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.0.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.1.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.1.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.1.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.10.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.10.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.10.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.100.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.100.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.100.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.101.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.101.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.101.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.102.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.102.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.102.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.103.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.103.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.103.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.104.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.104.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.104.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.105.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.105.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.105.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.106.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.106.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.106.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.107.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.107.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.107.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.108.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.108.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.108.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.109.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.109.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.109.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.11.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.11.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.11.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.110.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.110.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.110.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.111.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.111.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.111.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.112.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.112.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.112.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.113.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.113.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.113.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.114.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.114.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.114.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.115.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.115.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.115.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.116.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.116.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.116.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.117.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.117.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.117.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.118.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.118.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.118.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.119.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.119.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.119.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.12.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.12.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.12.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.120.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.120.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.120.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.121.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.121.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.121.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.122.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.122.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.122.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.123.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.123.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.123.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.124.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.124.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.124.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.125.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.125.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.125.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.126.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.126.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.126.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.127.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.127.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.127.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.128.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.128.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.128.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.129.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.129.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.129.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.13.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.13.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.13.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.130.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.130.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.130.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.131.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.131.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.131.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.132.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.132.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.132.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.133.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.133.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.133.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.134.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.134.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.134.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.135.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.135.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.135.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.136.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.136.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.136.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.137.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.137.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.137.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.138.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.138.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.138.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.139.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.139.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.139.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.14.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.14.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.14.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.140.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.140.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.140.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.141.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.141.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.141.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.142.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.142.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.142.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.143.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.143.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.143.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.144.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.144.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.144.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.145.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.145.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.145.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.146.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.146.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.146.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.147.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.147.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.147.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.148.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.148.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.148.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.149.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.149.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.149.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.15.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.15.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.15.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.150.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.150.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.150.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.151.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.151.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.151.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.152.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.152.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.152.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.153.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.153.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.153.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.154.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.154.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.154.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.155.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.155.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.155.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.156.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.156.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.156.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.157.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.157.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.157.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.158.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.158.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.158.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.159.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.159.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.159.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.16.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.16.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.16.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.17.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.17.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.17.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.18.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.18.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.18.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.19.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.19.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.19.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.2.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.2.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.2.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.20.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.20.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.20.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.21.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.21.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.21.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.22.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.22.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.22.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.23.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.23.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.23.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.24.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.24.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.24.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.25.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.25.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.25.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.26.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.26.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.26.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.27.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.27.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.27.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.28.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.28.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.28.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.29.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.29.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.29.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.3.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.3.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.3.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.30.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.30.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.30.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.31.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.31.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.31.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.32.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.32.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.32.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.33.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.33.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.33.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.34.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.34.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.34.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.35.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.35.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.35.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.36.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.36.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.36.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.37.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.37.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.37.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.38.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.38.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.38.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.39.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.39.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.39.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.4.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.4.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.4.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.40.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.40.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.40.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.41.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.41.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.41.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.42.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.42.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.42.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.43.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.43.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.43.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.44.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.44.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.44.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.45.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.45.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.45.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.46.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.46.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.46.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.47.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.47.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.47.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.48.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.48.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.48.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.49.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.49.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.49.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.5.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.5.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.5.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.50.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.50.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.50.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.51.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.51.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.51.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.52.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.52.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.52.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.53.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.53.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.53.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.54.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.54.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.54.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.55.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.55.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.55.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.56.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.56.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.56.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.57.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.57.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.57.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.58.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.58.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.58.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.59.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.59.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.59.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.6.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.6.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.6.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.60.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.60.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.60.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.61.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.61.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.61.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.62.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.62.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.62.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.63.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.63.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.63.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.64.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.64.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.64.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.65.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.65.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.65.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.66.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.66.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.66.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.67.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.67.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.67.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.68.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.68.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.68.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.69.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.69.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.69.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.7.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.7.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.7.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.70.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.70.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.70.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.71.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.71.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.71.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.72.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.72.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.72.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.73.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.73.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.73.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.74.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.74.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.74.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.75.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.75.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.75.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.76.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.76.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.76.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.77.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.77.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.77.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.78.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.78.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.78.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.79.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.79.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.79.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.8.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.8.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.8.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.80.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.80.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.80.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.81.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.81.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.81.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.82.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.82.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.82.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.83.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.83.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.83.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.84.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.84.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.84.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.85.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.85.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.85.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.86.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.86.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.86.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.87.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.87.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.87.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.88.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.88.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.88.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.89.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.89.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.89.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.9.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.9.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.9.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.90.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.90.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.90.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.91.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.91.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.91.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.92.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.92.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.92.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.93.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.93.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.93.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.94.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.94.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.94.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.95.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.95.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.95.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.96.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.96.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.96.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.97.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.97.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.97.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.98.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.98.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.98.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.99.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.99.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.experts.99.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.gate.e_score_correction_bias": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.gate.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.shared_experts.down_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.shared_experts.gate_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.mlp.shared_experts.up_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.post_attention_layernorm.weight": "model-00062-of-00092.safetensors", + "model.layers.61.self_attn.k_norm.weight": "model-00062-of-00092.safetensors", + "model.layers.61.self_attn.k_proj.bias": "model-00062-of-00092.safetensors", + "model.layers.61.self_attn.k_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.self_attn.o_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.self_attn.q_norm.weight": "model-00062-of-00092.safetensors", + "model.layers.61.self_attn.q_proj.bias": "model-00062-of-00092.safetensors", + "model.layers.61.self_attn.q_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.61.self_attn.v_proj.bias": "model-00062-of-00092.safetensors", + "model.layers.61.self_attn.v_proj.weight": "model-00062-of-00092.safetensors", + "model.layers.62.input_layernorm.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.0.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.0.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.0.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.1.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.1.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.1.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.10.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.10.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.10.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.100.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.100.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.100.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.101.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.101.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.101.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.102.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.102.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.102.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.103.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.103.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.103.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.104.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.104.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.104.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.105.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.105.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.105.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.106.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.106.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.106.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.107.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.107.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.107.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.108.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.108.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.108.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.109.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.109.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.109.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.11.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.11.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.11.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.110.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.110.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.110.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.111.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.111.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.111.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.112.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.112.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.112.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.113.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.113.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.113.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.114.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.114.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.114.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.115.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.115.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.115.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.116.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.116.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.116.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.117.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.117.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.117.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.118.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.118.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.118.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.119.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.119.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.119.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.12.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.12.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.12.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.120.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.120.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.120.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.121.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.121.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.121.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.122.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.122.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.122.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.123.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.123.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.123.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.124.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.124.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.124.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.125.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.125.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.125.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.126.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.126.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.126.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.127.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.127.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.127.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.128.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.128.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.128.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.129.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.129.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.129.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.13.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.13.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.13.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.130.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.130.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.130.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.131.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.131.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.131.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.132.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.132.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.132.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.133.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.133.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.133.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.134.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.134.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.134.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.135.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.135.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.135.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.136.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.136.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.136.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.137.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.137.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.137.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.138.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.138.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.138.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.139.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.139.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.139.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.14.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.14.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.14.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.140.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.140.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.140.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.141.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.141.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.141.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.142.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.142.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.142.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.143.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.143.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.143.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.144.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.144.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.144.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.145.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.145.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.145.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.146.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.146.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.146.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.147.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.147.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.147.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.148.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.148.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.148.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.149.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.149.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.149.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.15.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.15.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.15.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.150.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.150.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.150.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.151.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.151.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.151.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.152.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.152.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.152.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.153.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.153.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.153.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.154.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.154.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.154.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.155.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.155.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.155.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.156.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.156.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.156.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.157.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.157.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.157.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.158.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.158.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.158.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.159.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.159.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.159.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.16.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.16.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.16.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.17.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.17.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.17.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.18.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.18.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.18.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.19.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.19.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.19.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.2.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.2.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.2.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.20.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.20.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.20.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.21.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.21.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.21.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.22.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.22.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.22.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.23.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.23.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.23.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.24.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.24.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.24.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.25.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.25.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.25.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.26.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.26.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.26.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.27.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.27.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.27.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.28.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.28.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.28.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.29.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.29.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.29.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.3.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.3.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.3.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.30.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.30.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.30.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.31.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.31.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.31.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.32.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.32.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.32.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.33.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.33.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.33.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.34.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.34.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.34.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.35.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.35.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.35.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.36.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.36.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.36.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.37.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.37.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.37.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.38.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.38.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.38.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.39.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.39.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.39.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.4.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.4.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.4.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.40.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.40.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.40.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.41.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.41.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.41.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.42.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.42.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.42.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.43.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.43.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.43.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.44.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.44.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.44.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.45.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.45.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.45.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.46.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.46.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.46.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.47.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.47.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.47.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.48.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.48.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.48.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.49.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.49.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.49.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.5.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.5.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.5.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.50.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.50.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.50.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.51.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.51.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.51.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.52.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.52.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.52.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.53.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.53.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.53.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.54.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.54.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.54.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.55.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.55.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.55.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.56.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.56.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.56.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.57.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.57.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.57.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.58.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.58.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.58.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.59.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.59.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.59.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.6.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.6.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.6.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.60.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.60.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.60.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.61.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.61.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.61.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.62.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.62.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.62.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.63.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.63.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.63.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.64.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.64.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.64.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.65.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.65.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.65.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.66.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.66.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.66.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.67.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.67.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.67.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.68.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.68.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.68.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.69.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.69.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.69.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.7.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.7.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.7.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.70.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.70.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.70.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.71.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.71.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.71.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.72.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.72.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.72.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.73.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.73.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.73.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.74.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.74.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.74.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.75.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.75.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.75.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.76.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.76.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.76.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.77.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.77.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.77.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.78.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.78.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.78.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.79.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.79.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.79.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.8.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.8.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.8.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.80.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.80.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.80.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.81.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.81.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.81.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.82.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.82.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.82.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.83.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.83.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.83.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.84.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.84.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.84.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.85.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.85.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.85.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.86.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.86.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.86.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.87.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.87.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.87.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.88.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.88.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.88.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.89.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.89.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.89.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.9.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.9.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.9.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.90.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.90.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.90.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.91.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.91.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.91.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.92.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.92.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.92.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.93.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.93.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.93.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.94.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.94.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.94.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.95.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.95.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.95.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.96.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.96.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.96.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.97.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.97.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.97.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.98.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.98.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.98.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.99.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.99.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.experts.99.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.gate.e_score_correction_bias": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.gate.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.shared_experts.down_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.shared_experts.gate_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.mlp.shared_experts.up_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.post_attention_layernorm.weight": "model-00063-of-00092.safetensors", + "model.layers.62.self_attn.k_norm.weight": "model-00063-of-00092.safetensors", + "model.layers.62.self_attn.k_proj.bias": "model-00063-of-00092.safetensors", + "model.layers.62.self_attn.k_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.self_attn.o_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.self_attn.q_norm.weight": "model-00063-of-00092.safetensors", + "model.layers.62.self_attn.q_proj.bias": "model-00063-of-00092.safetensors", + "model.layers.62.self_attn.q_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.62.self_attn.v_proj.bias": "model-00063-of-00092.safetensors", + "model.layers.62.self_attn.v_proj.weight": "model-00063-of-00092.safetensors", + "model.layers.63.input_layernorm.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.0.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.0.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.0.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.1.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.1.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.1.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.10.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.10.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.10.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.100.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.100.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.100.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.101.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.101.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.101.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.102.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.102.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.102.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.103.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.103.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.103.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.104.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.104.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.104.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.105.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.105.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.105.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.106.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.106.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.106.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.107.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.107.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.107.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.108.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.108.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.108.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.109.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.109.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.109.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.11.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.11.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.11.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.110.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.110.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.110.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.111.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.111.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.111.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.112.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.112.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.112.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.113.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.113.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.113.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.114.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.114.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.114.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.115.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.115.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.115.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.116.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.116.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.116.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.117.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.117.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.117.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.118.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.118.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.118.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.119.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.119.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.119.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.12.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.12.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.12.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.120.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.120.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.120.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.121.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.121.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.121.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.122.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.122.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.122.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.123.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.123.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.123.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.124.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.124.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.124.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.125.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.125.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.125.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.126.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.126.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.126.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.127.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.127.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.127.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.128.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.128.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.128.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.129.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.129.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.129.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.13.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.13.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.13.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.130.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.130.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.130.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.131.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.131.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.131.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.132.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.132.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.132.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.133.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.133.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.133.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.134.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.134.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.134.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.135.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.135.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.135.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.136.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.136.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.136.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.137.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.137.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.137.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.138.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.138.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.138.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.139.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.139.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.139.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.14.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.14.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.14.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.140.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.140.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.140.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.141.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.141.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.141.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.142.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.142.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.142.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.143.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.143.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.143.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.144.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.144.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.144.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.145.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.145.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.145.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.146.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.146.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.146.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.147.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.147.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.147.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.148.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.148.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.148.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.149.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.149.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.149.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.15.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.15.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.15.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.150.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.150.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.150.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.151.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.151.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.151.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.152.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.152.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.152.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.153.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.153.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.153.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.154.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.154.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.154.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.155.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.155.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.155.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.156.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.156.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.156.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.157.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.157.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.157.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.158.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.158.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.158.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.159.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.159.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.159.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.16.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.16.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.16.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.17.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.17.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.17.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.18.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.18.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.18.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.19.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.19.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.19.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.2.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.2.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.2.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.20.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.20.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.20.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.21.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.21.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.21.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.22.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.22.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.22.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.23.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.23.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.23.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.24.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.24.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.24.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.25.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.25.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.25.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.26.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.26.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.26.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.27.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.27.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.27.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.28.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.28.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.28.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.29.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.29.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.29.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.3.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.3.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.3.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.30.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.30.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.30.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.31.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.31.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.31.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.32.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.32.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.32.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.33.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.33.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.33.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.34.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.34.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.34.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.35.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.35.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.35.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.36.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.36.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.36.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.37.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.37.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.37.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.38.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.38.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.38.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.39.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.39.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.39.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.4.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.4.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.4.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.40.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.40.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.40.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.41.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.41.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.41.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.42.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.42.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.42.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.43.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.43.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.43.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.44.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.44.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.44.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.45.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.45.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.45.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.46.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.46.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.46.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.47.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.47.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.47.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.48.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.48.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.48.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.49.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.49.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.49.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.5.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.5.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.5.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.50.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.50.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.50.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.51.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.51.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.51.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.52.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.52.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.52.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.53.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.53.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.53.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.54.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.54.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.54.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.55.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.55.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.55.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.56.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.56.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.56.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.57.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.57.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.57.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.58.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.58.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.58.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.59.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.59.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.59.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.6.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.6.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.6.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.60.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.60.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.60.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.61.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.61.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.61.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.62.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.62.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.62.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.63.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.63.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.63.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.64.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.64.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.64.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.65.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.65.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.65.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.66.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.66.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.66.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.67.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.67.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.67.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.68.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.68.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.68.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.69.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.69.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.69.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.7.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.7.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.7.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.70.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.70.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.70.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.71.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.71.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.71.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.72.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.72.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.72.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.73.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.73.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.73.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.74.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.74.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.74.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.75.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.75.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.75.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.76.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.76.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.76.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.77.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.77.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.77.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.78.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.78.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.78.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.79.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.79.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.79.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.8.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.8.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.8.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.80.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.80.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.80.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.81.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.81.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.81.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.82.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.82.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.82.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.83.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.83.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.83.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.84.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.84.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.84.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.85.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.85.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.85.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.86.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.86.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.86.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.87.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.87.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.87.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.88.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.88.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.88.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.89.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.89.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.89.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.9.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.9.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.9.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.90.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.90.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.90.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.91.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.91.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.91.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.92.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.92.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.92.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.93.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.93.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.93.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.94.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.94.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.94.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.95.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.95.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.95.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.96.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.96.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.96.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.97.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.97.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.97.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.98.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.98.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.98.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.99.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.99.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.experts.99.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.gate.e_score_correction_bias": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.gate.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.shared_experts.down_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.shared_experts.gate_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.mlp.shared_experts.up_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.post_attention_layernorm.weight": "model-00064-of-00092.safetensors", + "model.layers.63.self_attn.k_norm.weight": "model-00064-of-00092.safetensors", + "model.layers.63.self_attn.k_proj.bias": "model-00064-of-00092.safetensors", + "model.layers.63.self_attn.k_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.self_attn.o_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.self_attn.q_norm.weight": "model-00064-of-00092.safetensors", + "model.layers.63.self_attn.q_proj.bias": "model-00064-of-00092.safetensors", + "model.layers.63.self_attn.q_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.63.self_attn.v_proj.bias": "model-00064-of-00092.safetensors", + "model.layers.63.self_attn.v_proj.weight": "model-00064-of-00092.safetensors", + "model.layers.64.input_layernorm.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.0.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.0.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.0.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.1.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.1.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.1.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.10.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.10.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.10.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.100.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.100.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.100.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.101.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.101.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.101.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.102.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.102.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.102.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.103.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.103.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.103.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.104.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.104.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.104.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.105.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.105.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.105.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.106.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.106.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.106.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.107.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.107.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.107.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.108.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.108.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.108.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.109.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.109.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.109.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.11.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.11.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.11.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.110.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.110.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.110.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.111.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.111.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.111.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.112.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.112.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.112.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.113.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.113.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.113.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.114.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.114.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.114.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.115.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.115.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.115.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.116.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.116.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.116.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.117.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.117.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.117.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.118.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.118.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.118.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.119.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.119.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.119.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.12.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.12.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.12.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.120.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.120.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.120.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.121.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.121.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.121.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.122.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.122.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.122.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.123.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.123.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.123.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.124.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.124.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.124.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.125.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.125.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.125.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.126.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.126.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.126.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.127.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.127.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.127.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.128.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.128.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.128.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.129.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.129.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.129.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.13.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.13.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.13.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.130.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.130.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.130.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.131.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.131.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.131.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.132.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.132.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.132.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.133.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.133.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.133.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.134.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.134.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.134.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.135.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.135.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.135.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.136.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.136.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.136.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.137.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.137.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.137.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.138.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.138.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.138.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.139.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.139.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.139.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.14.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.14.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.14.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.140.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.140.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.140.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.141.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.141.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.141.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.142.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.142.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.142.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.143.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.143.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.143.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.144.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.144.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.144.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.145.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.145.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.145.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.146.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.146.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.146.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.147.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.147.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.147.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.148.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.148.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.148.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.149.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.149.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.149.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.15.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.15.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.15.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.150.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.150.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.150.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.151.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.151.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.151.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.152.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.152.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.152.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.153.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.153.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.153.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.154.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.154.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.154.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.155.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.155.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.155.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.156.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.156.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.156.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.157.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.157.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.157.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.158.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.158.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.158.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.159.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.159.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.159.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.16.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.16.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.16.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.17.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.17.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.17.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.18.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.18.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.18.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.19.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.19.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.19.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.2.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.2.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.2.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.20.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.20.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.20.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.21.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.21.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.21.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.22.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.22.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.22.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.23.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.23.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.23.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.24.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.24.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.24.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.25.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.25.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.25.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.26.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.26.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.26.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.27.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.27.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.27.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.28.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.28.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.28.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.29.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.29.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.29.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.3.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.3.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.3.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.30.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.30.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.30.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.31.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.31.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.31.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.32.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.32.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.32.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.33.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.33.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.33.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.34.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.34.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.34.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.35.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.35.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.35.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.36.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.36.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.36.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.37.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.37.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.37.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.38.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.38.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.38.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.39.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.39.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.39.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.4.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.4.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.4.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.40.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.40.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.40.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.41.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.41.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.41.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.42.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.42.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.42.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.43.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.43.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.43.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.44.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.44.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.44.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.45.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.45.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.45.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.46.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.46.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.46.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.47.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.47.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.47.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.48.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.48.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.48.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.49.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.49.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.49.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.5.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.5.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.5.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.50.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.50.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.50.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.51.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.51.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.51.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.52.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.52.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.52.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.53.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.53.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.53.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.54.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.54.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.54.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.55.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.55.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.55.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.56.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.56.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.56.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.57.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.57.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.57.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.58.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.58.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.58.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.59.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.59.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.59.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.6.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.6.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.6.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.60.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.60.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.60.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.61.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.61.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.61.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.62.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.62.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.62.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.63.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.63.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.63.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.64.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.64.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.64.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.65.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.65.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.65.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.66.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.66.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.66.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.67.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.67.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.67.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.68.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.68.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.68.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.69.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.69.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.69.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.7.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.7.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.7.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.70.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.70.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.70.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.71.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.71.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.71.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.72.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.72.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.72.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.73.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.73.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.73.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.74.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.74.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.74.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.75.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.75.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.75.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.76.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.76.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.76.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.77.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.77.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.77.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.78.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.78.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.78.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.79.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.79.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.79.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.8.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.8.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.8.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.80.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.80.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.80.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.81.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.81.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.81.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.82.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.82.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.82.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.83.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.83.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.83.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.84.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.84.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.84.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.85.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.85.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.85.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.86.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.86.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.86.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.87.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.87.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.87.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.88.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.88.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.88.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.89.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.89.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.89.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.9.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.9.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.9.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.90.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.90.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.90.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.91.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.91.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.91.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.92.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.92.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.92.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.93.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.93.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.93.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.94.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.94.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.94.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.95.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.95.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.95.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.96.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.96.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.96.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.97.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.97.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.97.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.98.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.98.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.98.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.99.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.99.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.experts.99.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.gate.e_score_correction_bias": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.gate.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.shared_experts.down_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.shared_experts.gate_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.mlp.shared_experts.up_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.post_attention_layernorm.weight": "model-00065-of-00092.safetensors", + "model.layers.64.self_attn.k_norm.weight": "model-00065-of-00092.safetensors", + "model.layers.64.self_attn.k_proj.bias": "model-00065-of-00092.safetensors", + "model.layers.64.self_attn.k_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.self_attn.o_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.self_attn.q_norm.weight": "model-00065-of-00092.safetensors", + "model.layers.64.self_attn.q_proj.bias": "model-00065-of-00092.safetensors", + "model.layers.64.self_attn.q_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.64.self_attn.v_proj.bias": "model-00065-of-00092.safetensors", + "model.layers.64.self_attn.v_proj.weight": "model-00065-of-00092.safetensors", + "model.layers.65.input_layernorm.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.0.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.0.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.0.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.1.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.1.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.1.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.10.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.10.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.10.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.100.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.100.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.100.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.101.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.101.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.101.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.102.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.102.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.102.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.103.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.103.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.103.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.104.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.104.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.104.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.105.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.105.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.105.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.106.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.106.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.106.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.107.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.107.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.107.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.108.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.108.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.108.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.109.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.109.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.109.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.11.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.11.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.11.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.110.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.110.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.110.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.111.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.111.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.111.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.112.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.112.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.112.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.113.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.113.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.113.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.114.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.114.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.114.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.115.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.115.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.115.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.116.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.116.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.116.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.117.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.117.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.117.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.118.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.118.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.118.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.119.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.119.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.119.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.12.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.12.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.12.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.120.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.120.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.120.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.121.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.121.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.121.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.122.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.122.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.122.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.123.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.123.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.123.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.124.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.124.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.124.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.125.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.125.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.125.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.126.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.126.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.126.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.127.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.127.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.127.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.128.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.128.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.128.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.129.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.129.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.129.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.13.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.13.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.13.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.130.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.130.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.130.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.131.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.131.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.131.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.132.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.132.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.132.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.133.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.133.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.133.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.134.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.134.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.134.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.135.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.135.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.135.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.136.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.136.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.136.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.137.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.137.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.137.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.138.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.138.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.138.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.139.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.139.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.139.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.14.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.14.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.14.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.140.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.140.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.140.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.141.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.141.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.141.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.142.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.142.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.142.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.143.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.143.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.143.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.144.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.144.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.144.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.145.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.145.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.145.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.146.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.146.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.146.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.147.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.147.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.147.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.148.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.148.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.148.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.149.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.149.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.149.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.15.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.15.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.15.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.150.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.150.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.150.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.151.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.151.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.151.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.152.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.152.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.152.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.153.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.153.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.153.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.154.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.154.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.154.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.155.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.155.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.155.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.156.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.156.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.156.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.157.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.157.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.157.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.158.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.158.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.158.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.159.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.159.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.159.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.16.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.16.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.16.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.17.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.17.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.17.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.18.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.18.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.18.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.19.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.19.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.19.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.2.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.2.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.2.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.20.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.20.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.20.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.21.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.21.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.21.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.22.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.22.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.22.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.23.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.23.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.23.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.24.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.24.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.24.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.25.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.25.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.25.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.26.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.26.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.26.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.27.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.27.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.27.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.28.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.28.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.28.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.29.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.29.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.29.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.3.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.3.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.3.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.30.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.30.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.30.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.31.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.31.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.31.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.32.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.32.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.32.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.33.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.33.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.33.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.34.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.34.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.34.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.35.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.35.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.35.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.36.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.36.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.36.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.37.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.37.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.37.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.38.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.38.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.38.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.39.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.39.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.39.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.4.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.4.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.4.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.40.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.40.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.40.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.41.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.41.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.41.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.42.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.42.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.42.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.43.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.43.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.43.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.44.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.44.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.44.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.45.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.45.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.45.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.46.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.46.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.46.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.47.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.47.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.47.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.48.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.48.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.48.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.49.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.49.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.49.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.5.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.5.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.5.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.50.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.50.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.50.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.51.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.51.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.51.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.52.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.52.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.52.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.53.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.53.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.53.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.54.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.54.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.54.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.55.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.55.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.55.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.56.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.56.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.56.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.57.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.57.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.57.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.58.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.58.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.58.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.59.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.59.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.59.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.6.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.6.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.6.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.60.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.60.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.60.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.61.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.61.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.61.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.62.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.62.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.62.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.63.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.63.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.63.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.64.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.64.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.64.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.65.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.65.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.65.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.66.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.66.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.66.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.67.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.67.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.67.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.68.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.68.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.68.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.69.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.69.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.69.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.7.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.7.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.7.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.70.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.70.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.70.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.71.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.71.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.71.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.72.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.72.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.72.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.73.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.73.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.73.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.74.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.74.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.74.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.75.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.75.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.75.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.76.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.76.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.76.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.77.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.77.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.77.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.78.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.78.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.78.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.79.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.79.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.79.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.8.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.8.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.8.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.80.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.80.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.80.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.81.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.81.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.81.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.82.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.82.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.82.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.83.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.83.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.83.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.84.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.84.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.84.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.85.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.85.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.85.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.86.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.86.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.86.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.87.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.87.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.87.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.88.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.88.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.88.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.89.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.89.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.89.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.9.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.9.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.9.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.90.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.90.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.90.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.91.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.91.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.91.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.92.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.92.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.92.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.93.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.93.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.93.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.94.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.94.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.94.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.95.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.95.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.95.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.96.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.96.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.96.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.97.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.97.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.97.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.98.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.98.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.98.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.99.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.99.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.experts.99.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.gate.e_score_correction_bias": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.gate.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.shared_experts.down_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.shared_experts.gate_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.mlp.shared_experts.up_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.post_attention_layernorm.weight": "model-00066-of-00092.safetensors", + "model.layers.65.self_attn.k_norm.weight": "model-00066-of-00092.safetensors", + "model.layers.65.self_attn.k_proj.bias": "model-00066-of-00092.safetensors", + "model.layers.65.self_attn.k_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.self_attn.o_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.self_attn.q_norm.weight": "model-00066-of-00092.safetensors", + "model.layers.65.self_attn.q_proj.bias": "model-00066-of-00092.safetensors", + "model.layers.65.self_attn.q_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.65.self_attn.v_proj.bias": "model-00066-of-00092.safetensors", + "model.layers.65.self_attn.v_proj.weight": "model-00066-of-00092.safetensors", + "model.layers.66.input_layernorm.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.0.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.0.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.0.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.1.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.1.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.1.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.10.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.10.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.10.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.100.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.100.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.100.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.101.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.101.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.101.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.102.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.102.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.102.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.103.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.103.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.103.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.104.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.104.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.104.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.105.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.105.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.105.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.106.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.106.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.106.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.107.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.107.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.107.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.108.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.108.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.108.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.109.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.109.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.109.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.11.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.11.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.11.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.110.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.110.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.110.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.111.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.111.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.111.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.112.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.112.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.112.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.113.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.113.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.113.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.114.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.114.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.114.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.115.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.115.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.115.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.116.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.116.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.116.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.117.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.117.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.117.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.118.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.118.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.118.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.119.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.119.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.119.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.12.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.12.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.12.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.120.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.120.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.120.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.121.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.121.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.121.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.122.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.122.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.122.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.123.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.123.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.123.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.124.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.124.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.124.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.125.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.125.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.125.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.126.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.126.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.126.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.127.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.127.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.127.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.128.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.128.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.128.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.129.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.129.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.129.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.13.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.13.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.13.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.130.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.130.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.130.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.131.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.131.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.131.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.132.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.132.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.132.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.133.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.133.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.133.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.134.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.134.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.134.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.135.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.135.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.135.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.136.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.136.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.136.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.137.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.137.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.137.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.138.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.138.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.138.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.139.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.139.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.139.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.14.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.14.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.14.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.140.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.140.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.140.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.141.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.141.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.141.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.142.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.142.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.142.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.143.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.143.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.143.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.144.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.144.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.144.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.145.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.145.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.145.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.146.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.146.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.146.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.147.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.147.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.147.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.148.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.148.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.148.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.149.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.149.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.149.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.15.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.15.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.15.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.150.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.150.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.150.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.151.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.151.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.151.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.152.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.152.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.152.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.153.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.153.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.153.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.154.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.154.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.154.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.155.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.155.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.155.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.156.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.156.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.156.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.157.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.157.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.157.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.158.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.158.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.158.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.159.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.159.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.159.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.16.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.16.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.16.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.17.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.17.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.17.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.18.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.18.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.18.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.19.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.19.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.19.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.2.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.2.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.2.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.20.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.20.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.20.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.21.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.21.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.21.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.22.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.22.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.22.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.23.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.23.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.23.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.24.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.24.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.24.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.25.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.25.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.25.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.26.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.26.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.26.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.27.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.27.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.27.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.28.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.28.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.28.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.29.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.29.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.29.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.3.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.3.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.3.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.30.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.30.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.30.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.31.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.31.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.31.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.32.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.32.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.32.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.33.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.33.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.33.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.34.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.34.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.34.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.35.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.35.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.35.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.36.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.36.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.36.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.37.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.37.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.37.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.38.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.38.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.38.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.39.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.39.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.39.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.4.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.4.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.4.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.40.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.40.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.40.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.41.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.41.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.41.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.42.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.42.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.42.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.43.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.43.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.43.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.44.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.44.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.44.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.45.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.45.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.45.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.46.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.46.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.46.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.47.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.47.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.47.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.48.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.48.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.48.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.49.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.49.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.49.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.5.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.5.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.5.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.50.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.50.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.50.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.51.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.51.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.51.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.52.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.52.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.52.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.53.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.53.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.53.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.54.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.54.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.54.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.55.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.55.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.55.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.56.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.56.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.56.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.57.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.57.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.57.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.58.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.58.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.58.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.59.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.59.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.59.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.6.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.6.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.6.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.60.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.60.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.60.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.61.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.61.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.61.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.62.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.62.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.62.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.63.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.63.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.63.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.64.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.64.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.64.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.65.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.65.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.65.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.66.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.66.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.66.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.67.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.67.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.67.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.68.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.68.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.68.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.69.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.69.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.69.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.7.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.7.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.7.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.70.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.70.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.70.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.71.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.71.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.71.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.72.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.72.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.72.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.73.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.73.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.73.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.74.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.74.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.74.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.75.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.75.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.75.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.76.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.76.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.76.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.77.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.77.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.77.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.78.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.78.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.78.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.79.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.79.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.79.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.8.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.8.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.8.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.80.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.80.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.80.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.81.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.81.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.81.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.82.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.82.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.82.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.83.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.83.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.83.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.84.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.84.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.84.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.85.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.85.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.85.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.86.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.86.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.86.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.87.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.87.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.87.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.88.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.88.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.88.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.89.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.89.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.89.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.9.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.9.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.9.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.90.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.90.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.90.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.91.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.91.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.91.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.92.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.92.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.92.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.93.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.93.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.93.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.94.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.94.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.94.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.95.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.95.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.95.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.96.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.96.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.96.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.97.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.97.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.97.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.98.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.98.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.98.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.99.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.99.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.experts.99.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.gate.e_score_correction_bias": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.gate.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.shared_experts.down_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.shared_experts.gate_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.mlp.shared_experts.up_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.post_attention_layernorm.weight": "model-00067-of-00092.safetensors", + "model.layers.66.self_attn.k_norm.weight": "model-00067-of-00092.safetensors", + "model.layers.66.self_attn.k_proj.bias": "model-00067-of-00092.safetensors", + "model.layers.66.self_attn.k_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.self_attn.o_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.self_attn.q_norm.weight": "model-00067-of-00092.safetensors", + "model.layers.66.self_attn.q_proj.bias": "model-00067-of-00092.safetensors", + "model.layers.66.self_attn.q_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.66.self_attn.v_proj.bias": "model-00067-of-00092.safetensors", + "model.layers.66.self_attn.v_proj.weight": "model-00067-of-00092.safetensors", + "model.layers.67.input_layernorm.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.0.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.0.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.0.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.1.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.1.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.1.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.10.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.10.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.10.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.100.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.100.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.100.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.101.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.101.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.101.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.102.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.102.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.102.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.103.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.103.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.103.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.104.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.104.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.104.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.105.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.105.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.105.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.106.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.106.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.106.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.107.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.107.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.107.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.108.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.108.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.108.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.109.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.109.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.109.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.11.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.11.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.11.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.110.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.110.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.110.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.111.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.111.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.111.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.112.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.112.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.112.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.113.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.113.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.113.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.114.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.114.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.114.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.115.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.115.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.115.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.116.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.116.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.116.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.117.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.117.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.117.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.118.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.118.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.118.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.119.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.119.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.119.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.12.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.12.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.12.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.120.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.120.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.120.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.121.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.121.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.121.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.122.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.122.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.122.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.123.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.123.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.123.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.124.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.124.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.124.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.125.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.125.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.125.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.126.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.126.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.126.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.127.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.127.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.127.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.128.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.128.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.128.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.129.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.129.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.129.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.13.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.13.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.13.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.130.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.130.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.130.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.131.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.131.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.131.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.132.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.132.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.132.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.133.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.133.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.133.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.134.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.134.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.134.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.135.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.135.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.135.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.136.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.136.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.136.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.137.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.137.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.137.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.138.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.138.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.138.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.139.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.139.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.139.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.14.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.14.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.14.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.140.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.140.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.140.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.141.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.141.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.141.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.142.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.142.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.142.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.143.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.143.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.143.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.144.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.144.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.144.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.145.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.145.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.145.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.146.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.146.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.146.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.147.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.147.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.147.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.148.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.148.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.148.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.149.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.149.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.149.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.15.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.15.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.15.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.150.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.150.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.150.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.151.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.151.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.151.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.152.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.152.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.152.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.153.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.153.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.153.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.154.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.154.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.154.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.155.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.155.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.155.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.156.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.156.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.156.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.157.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.157.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.157.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.158.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.158.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.158.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.159.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.159.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.159.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.16.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.16.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.16.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.17.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.17.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.17.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.18.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.18.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.18.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.19.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.19.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.19.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.2.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.2.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.2.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.20.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.20.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.20.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.21.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.21.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.21.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.22.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.22.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.22.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.23.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.23.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.23.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.24.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.24.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.24.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.25.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.25.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.25.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.26.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.26.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.26.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.27.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.27.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.27.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.28.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.28.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.28.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.29.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.29.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.29.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.3.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.3.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.3.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.30.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.30.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.30.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.31.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.31.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.31.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.32.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.32.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.32.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.33.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.33.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.33.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.34.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.34.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.34.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.35.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.35.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.35.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.36.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.36.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.36.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.37.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.37.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.37.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.38.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.38.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.38.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.39.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.39.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.39.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.4.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.4.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.4.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.40.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.40.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.40.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.41.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.41.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.41.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.42.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.42.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.42.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.43.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.43.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.43.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.44.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.44.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.44.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.45.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.45.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.45.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.46.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.46.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.46.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.47.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.47.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.47.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.48.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.48.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.48.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.49.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.49.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.49.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.5.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.5.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.5.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.50.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.50.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.50.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.51.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.51.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.51.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.52.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.52.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.52.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.53.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.53.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.53.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.54.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.54.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.54.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.55.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.55.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.55.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.56.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.56.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.56.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.57.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.57.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.57.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.58.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.58.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.58.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.59.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.59.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.59.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.6.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.6.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.6.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.60.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.60.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.60.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.61.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.61.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.61.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.62.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.62.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.62.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.63.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.63.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.63.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.64.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.64.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.64.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.65.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.65.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.65.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.66.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.66.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.66.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.67.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.67.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.67.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.68.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.68.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.68.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.69.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.69.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.69.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.7.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.7.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.7.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.70.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.70.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.70.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.71.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.71.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.71.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.72.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.72.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.72.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.73.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.73.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.73.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.74.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.74.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.74.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.75.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.75.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.75.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.76.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.76.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.76.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.77.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.77.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.77.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.78.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.78.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.78.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.79.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.79.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.79.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.8.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.8.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.8.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.80.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.80.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.80.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.81.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.81.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.81.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.82.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.82.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.82.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.83.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.83.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.83.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.84.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.84.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.84.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.85.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.85.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.85.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.86.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.86.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.86.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.87.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.87.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.87.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.88.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.88.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.88.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.89.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.89.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.89.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.9.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.9.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.9.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.90.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.90.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.90.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.91.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.91.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.91.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.92.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.92.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.92.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.93.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.93.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.93.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.94.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.94.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.94.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.95.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.95.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.95.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.96.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.96.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.96.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.97.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.97.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.97.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.98.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.98.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.98.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.99.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.99.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.experts.99.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.gate.e_score_correction_bias": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.gate.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.shared_experts.down_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.shared_experts.gate_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.mlp.shared_experts.up_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.post_attention_layernorm.weight": "model-00068-of-00092.safetensors", + "model.layers.67.self_attn.k_norm.weight": "model-00068-of-00092.safetensors", + "model.layers.67.self_attn.k_proj.bias": "model-00068-of-00092.safetensors", + "model.layers.67.self_attn.k_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.self_attn.o_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.self_attn.q_norm.weight": "model-00068-of-00092.safetensors", + "model.layers.67.self_attn.q_proj.bias": "model-00068-of-00092.safetensors", + "model.layers.67.self_attn.q_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.67.self_attn.v_proj.bias": "model-00068-of-00092.safetensors", + "model.layers.67.self_attn.v_proj.weight": "model-00068-of-00092.safetensors", + "model.layers.68.input_layernorm.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.0.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.0.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.0.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.1.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.1.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.1.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.10.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.10.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.10.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.100.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.100.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.100.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.101.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.101.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.101.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.102.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.102.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.102.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.103.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.103.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.103.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.104.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.104.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.104.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.105.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.105.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.105.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.106.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.106.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.106.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.107.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.107.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.107.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.108.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.108.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.108.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.109.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.109.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.109.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.11.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.11.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.11.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.110.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.110.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.110.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.111.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.111.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.111.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.112.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.112.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.112.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.113.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.113.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.113.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.114.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.114.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.114.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.115.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.115.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.115.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.116.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.116.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.116.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.117.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.117.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.117.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.118.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.118.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.118.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.119.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.119.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.119.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.12.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.12.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.12.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.120.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.120.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.120.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.121.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.121.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.121.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.122.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.122.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.122.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.123.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.123.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.123.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.124.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.124.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.124.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.125.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.125.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.125.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.126.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.126.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.126.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.127.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.127.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.127.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.128.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.128.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.128.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.129.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.129.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.129.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.13.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.13.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.13.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.130.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.130.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.130.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.131.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.131.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.131.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.132.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.132.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.132.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.133.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.133.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.133.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.134.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.134.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.134.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.135.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.135.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.135.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.136.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.136.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.136.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.137.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.137.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.137.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.138.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.138.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.138.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.139.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.139.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.139.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.14.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.14.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.14.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.140.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.140.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.140.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.141.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.141.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.141.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.142.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.142.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.142.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.143.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.143.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.143.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.144.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.144.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.144.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.145.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.145.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.145.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.146.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.146.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.146.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.147.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.147.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.147.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.148.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.148.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.148.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.149.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.149.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.149.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.15.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.15.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.15.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.150.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.150.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.150.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.151.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.151.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.151.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.152.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.152.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.152.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.153.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.153.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.153.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.154.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.154.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.154.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.155.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.155.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.155.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.156.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.156.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.156.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.157.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.157.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.157.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.158.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.158.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.158.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.159.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.159.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.159.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.16.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.16.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.16.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.17.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.17.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.17.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.18.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.18.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.18.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.19.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.19.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.19.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.2.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.2.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.2.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.20.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.20.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.20.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.21.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.21.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.21.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.22.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.22.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.22.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.23.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.23.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.23.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.24.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.24.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.24.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.25.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.25.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.25.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.26.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.26.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.26.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.27.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.27.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.27.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.28.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.28.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.28.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.29.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.29.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.29.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.3.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.3.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.3.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.30.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.30.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.30.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.31.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.31.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.31.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.32.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.32.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.32.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.33.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.33.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.33.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.34.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.34.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.34.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.35.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.35.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.35.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.36.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.36.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.36.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.37.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.37.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.37.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.38.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.38.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.38.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.39.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.39.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.39.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.4.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.4.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.4.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.40.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.40.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.40.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.41.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.41.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.41.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.42.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.42.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.42.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.43.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.43.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.43.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.44.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.44.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.44.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.45.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.45.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.45.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.46.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.46.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.46.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.47.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.47.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.47.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.48.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.48.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.48.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.49.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.49.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.49.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.5.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.5.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.5.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.50.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.50.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.50.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.51.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.51.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.51.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.52.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.52.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.52.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.53.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.53.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.53.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.54.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.54.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.54.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.55.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.55.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.55.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.56.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.56.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.56.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.57.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.57.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.57.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.58.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.58.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.58.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.59.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.59.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.59.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.6.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.6.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.6.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.60.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.60.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.60.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.61.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.61.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.61.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.62.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.62.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.62.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.63.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.63.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.63.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.64.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.64.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.64.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.65.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.65.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.65.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.66.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.66.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.66.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.67.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.67.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.67.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.68.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.68.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.68.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.69.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.69.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.69.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.7.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.7.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.7.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.70.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.70.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.70.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.71.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.71.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.71.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.72.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.72.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.72.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.73.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.73.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.73.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.74.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.74.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.74.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.75.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.75.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.75.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.76.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.76.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.76.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.77.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.77.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.77.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.78.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.78.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.78.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.79.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.79.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.79.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.8.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.8.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.8.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.80.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.80.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.80.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.81.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.81.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.81.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.82.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.82.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.82.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.83.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.83.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.83.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.84.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.84.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.84.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.85.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.85.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.85.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.86.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.86.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.86.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.87.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.87.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.87.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.88.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.88.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.88.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.89.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.89.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.89.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.9.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.9.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.9.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.90.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.90.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.90.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.91.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.91.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.91.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.92.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.92.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.92.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.93.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.93.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.93.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.94.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.94.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.94.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.95.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.95.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.95.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.96.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.96.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.96.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.97.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.97.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.97.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.98.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.98.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.98.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.99.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.99.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.experts.99.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.gate.e_score_correction_bias": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.gate.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.shared_experts.down_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.shared_experts.gate_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.mlp.shared_experts.up_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.post_attention_layernorm.weight": "model-00069-of-00092.safetensors", + "model.layers.68.self_attn.k_norm.weight": "model-00069-of-00092.safetensors", + "model.layers.68.self_attn.k_proj.bias": "model-00069-of-00092.safetensors", + "model.layers.68.self_attn.k_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.self_attn.o_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.self_attn.q_norm.weight": "model-00069-of-00092.safetensors", + "model.layers.68.self_attn.q_proj.bias": "model-00069-of-00092.safetensors", + "model.layers.68.self_attn.q_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.68.self_attn.v_proj.bias": "model-00069-of-00092.safetensors", + "model.layers.68.self_attn.v_proj.weight": "model-00069-of-00092.safetensors", + "model.layers.69.input_layernorm.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.0.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.0.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.0.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.1.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.1.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.1.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.10.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.10.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.10.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.100.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.100.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.100.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.101.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.101.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.101.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.102.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.102.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.102.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.103.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.103.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.103.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.104.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.104.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.104.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.105.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.105.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.105.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.106.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.106.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.106.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.107.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.107.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.107.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.108.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.108.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.108.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.109.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.109.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.109.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.11.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.11.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.11.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.110.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.110.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.110.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.111.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.111.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.111.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.112.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.112.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.112.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.113.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.113.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.113.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.114.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.114.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.114.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.115.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.115.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.115.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.116.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.116.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.116.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.117.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.117.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.117.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.118.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.118.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.118.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.119.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.119.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.119.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.12.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.12.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.12.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.120.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.120.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.120.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.121.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.121.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.121.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.122.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.122.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.122.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.123.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.123.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.123.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.124.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.124.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.124.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.125.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.125.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.125.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.126.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.126.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.126.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.127.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.127.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.127.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.128.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.128.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.128.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.129.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.129.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.129.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.13.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.13.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.13.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.130.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.130.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.130.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.131.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.131.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.131.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.132.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.132.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.132.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.133.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.133.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.133.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.134.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.134.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.134.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.135.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.135.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.135.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.136.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.136.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.136.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.137.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.137.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.137.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.138.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.138.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.138.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.139.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.139.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.139.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.14.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.14.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.14.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.140.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.140.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.140.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.141.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.141.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.141.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.142.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.142.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.142.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.143.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.143.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.143.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.144.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.144.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.144.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.145.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.145.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.145.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.146.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.146.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.146.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.147.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.147.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.147.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.148.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.148.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.148.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.149.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.149.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.149.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.15.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.15.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.15.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.150.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.150.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.150.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.151.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.151.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.151.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.152.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.152.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.152.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.153.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.153.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.153.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.154.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.154.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.154.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.155.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.155.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.155.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.156.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.156.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.156.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.157.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.157.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.157.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.158.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.158.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.158.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.159.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.159.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.159.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.16.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.16.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.16.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.17.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.17.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.17.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.18.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.18.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.18.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.19.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.19.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.19.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.2.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.2.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.2.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.20.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.20.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.20.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.21.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.21.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.21.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.22.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.22.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.22.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.23.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.23.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.23.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.24.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.24.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.24.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.25.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.25.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.25.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.26.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.26.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.26.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.27.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.27.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.27.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.28.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.28.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.28.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.29.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.29.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.29.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.3.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.3.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.3.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.30.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.30.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.30.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.31.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.31.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.31.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.32.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.32.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.32.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.33.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.33.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.33.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.34.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.34.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.34.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.35.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.35.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.35.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.36.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.36.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.36.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.37.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.37.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.37.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.38.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.38.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.38.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.39.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.39.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.39.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.4.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.4.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.4.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.40.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.40.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.40.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.41.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.41.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.41.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.42.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.42.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.42.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.43.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.43.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.43.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.44.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.44.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.44.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.45.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.45.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.45.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.46.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.46.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.46.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.47.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.47.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.47.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.48.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.48.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.48.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.49.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.49.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.49.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.5.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.5.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.5.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.50.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.50.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.50.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.51.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.51.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.51.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.52.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.52.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.52.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.53.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.53.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.53.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.54.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.54.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.54.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.55.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.55.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.55.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.56.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.56.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.56.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.57.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.57.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.57.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.58.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.58.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.58.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.59.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.59.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.59.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.6.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.6.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.6.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.60.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.60.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.60.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.61.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.61.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.61.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.62.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.62.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.62.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.63.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.63.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.63.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.64.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.64.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.64.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.65.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.65.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.65.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.66.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.66.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.66.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.67.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.67.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.67.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.68.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.68.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.68.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.69.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.69.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.69.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.7.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.7.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.7.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.70.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.70.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.70.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.71.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.71.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.71.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.72.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.72.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.72.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.73.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.73.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.73.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.74.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.74.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.74.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.75.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.75.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.75.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.76.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.76.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.76.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.77.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.77.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.77.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.78.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.78.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.78.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.79.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.79.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.79.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.8.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.8.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.8.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.80.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.80.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.80.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.81.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.81.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.81.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.82.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.82.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.82.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.83.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.83.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.83.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.84.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.84.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.84.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.85.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.85.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.85.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.86.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.86.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.86.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.87.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.87.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.87.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.88.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.88.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.88.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.89.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.89.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.89.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.9.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.9.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.9.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.90.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.90.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.90.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.91.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.91.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.91.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.92.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.92.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.92.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.93.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.93.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.93.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.94.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.94.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.94.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.95.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.95.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.95.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.96.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.96.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.96.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.97.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.97.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.97.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.98.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.98.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.98.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.99.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.99.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.experts.99.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.gate.e_score_correction_bias": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.gate.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.shared_experts.down_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.shared_experts.gate_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.mlp.shared_experts.up_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.post_attention_layernorm.weight": "model-00070-of-00092.safetensors", + "model.layers.69.self_attn.k_norm.weight": "model-00070-of-00092.safetensors", + "model.layers.69.self_attn.k_proj.bias": "model-00070-of-00092.safetensors", + "model.layers.69.self_attn.k_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.self_attn.o_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.self_attn.q_norm.weight": "model-00070-of-00092.safetensors", + "model.layers.69.self_attn.q_proj.bias": "model-00070-of-00092.safetensors", + "model.layers.69.self_attn.q_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.69.self_attn.v_proj.bias": "model-00070-of-00092.safetensors", + "model.layers.69.self_attn.v_proj.weight": "model-00070-of-00092.safetensors", + "model.layers.70.input_layernorm.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.0.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.0.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.0.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.1.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.1.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.1.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.10.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.10.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.10.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.100.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.100.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.100.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.101.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.101.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.101.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.102.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.102.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.102.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.103.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.103.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.103.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.104.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.104.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.104.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.105.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.105.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.105.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.106.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.106.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.106.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.107.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.107.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.107.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.108.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.108.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.108.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.109.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.109.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.109.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.11.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.11.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.11.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.110.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.110.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.110.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.111.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.111.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.111.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.112.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.112.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.112.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.113.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.113.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.113.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.114.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.114.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.114.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.115.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.115.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.115.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.116.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.116.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.116.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.117.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.117.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.117.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.118.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.118.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.118.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.119.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.119.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.119.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.12.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.12.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.12.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.120.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.120.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.120.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.121.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.121.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.121.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.122.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.122.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.122.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.123.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.123.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.123.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.124.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.124.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.124.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.125.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.125.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.125.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.126.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.126.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.126.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.127.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.127.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.127.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.128.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.128.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.128.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.129.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.129.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.129.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.13.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.13.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.13.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.130.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.130.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.130.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.131.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.131.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.131.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.132.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.132.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.132.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.133.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.133.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.133.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.134.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.134.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.134.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.135.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.135.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.135.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.136.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.136.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.136.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.137.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.137.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.137.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.138.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.138.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.138.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.139.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.139.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.139.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.14.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.14.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.14.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.140.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.140.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.140.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.141.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.141.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.141.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.142.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.142.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.142.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.143.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.143.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.143.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.144.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.144.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.144.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.145.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.145.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.145.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.146.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.146.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.146.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.147.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.147.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.147.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.148.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.148.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.148.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.149.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.149.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.149.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.15.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.15.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.15.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.150.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.150.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.150.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.151.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.151.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.151.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.152.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.152.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.152.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.153.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.153.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.153.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.154.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.154.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.154.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.155.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.155.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.155.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.156.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.156.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.156.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.157.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.157.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.157.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.158.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.158.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.158.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.159.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.159.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.159.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.16.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.16.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.16.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.17.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.17.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.17.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.18.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.18.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.18.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.19.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.19.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.19.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.2.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.2.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.2.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.20.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.20.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.20.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.21.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.21.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.21.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.22.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.22.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.22.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.23.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.23.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.23.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.24.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.24.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.24.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.25.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.25.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.25.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.26.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.26.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.26.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.27.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.27.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.27.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.28.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.28.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.28.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.29.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.29.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.29.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.3.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.3.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.3.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.30.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.30.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.30.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.31.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.31.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.31.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.32.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.32.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.32.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.33.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.33.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.33.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.34.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.34.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.34.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.35.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.35.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.35.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.36.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.36.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.36.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.37.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.37.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.37.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.38.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.38.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.38.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.39.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.39.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.39.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.4.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.4.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.4.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.40.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.40.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.40.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.41.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.41.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.41.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.42.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.42.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.42.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.43.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.43.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.43.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.44.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.44.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.44.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.45.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.45.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.45.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.46.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.46.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.46.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.47.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.47.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.47.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.48.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.48.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.48.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.49.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.49.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.49.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.5.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.5.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.5.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.50.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.50.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.50.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.51.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.51.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.51.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.52.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.52.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.52.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.53.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.53.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.53.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.54.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.54.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.54.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.55.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.55.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.55.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.56.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.56.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.56.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.57.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.57.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.57.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.58.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.58.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.58.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.59.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.59.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.59.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.6.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.6.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.6.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.60.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.60.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.60.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.61.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.61.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.61.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.62.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.62.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.62.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.63.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.63.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.63.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.64.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.64.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.64.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.65.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.65.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.65.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.66.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.66.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.66.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.67.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.67.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.67.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.68.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.68.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.68.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.69.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.69.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.69.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.7.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.7.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.7.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.70.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.70.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.70.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.71.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.71.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.71.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.72.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.72.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.72.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.73.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.73.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.73.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.74.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.74.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.74.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.75.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.75.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.75.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.76.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.76.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.76.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.77.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.77.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.77.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.78.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.78.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.78.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.79.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.79.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.79.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.8.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.8.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.8.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.80.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.80.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.80.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.81.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.81.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.81.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.82.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.82.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.82.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.83.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.83.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.83.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.84.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.84.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.84.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.85.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.85.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.85.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.86.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.86.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.86.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.87.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.87.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.87.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.88.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.88.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.88.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.89.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.89.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.89.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.9.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.9.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.9.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.90.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.90.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.90.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.91.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.91.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.91.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.92.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.92.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.92.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.93.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.93.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.93.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.94.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.94.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.94.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.95.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.95.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.95.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.96.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.96.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.96.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.97.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.97.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.97.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.98.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.98.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.98.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.99.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.99.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.experts.99.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.gate.e_score_correction_bias": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.gate.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.shared_experts.down_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.shared_experts.gate_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.mlp.shared_experts.up_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.post_attention_layernorm.weight": "model-00071-of-00092.safetensors", + "model.layers.70.self_attn.k_norm.weight": "model-00071-of-00092.safetensors", + "model.layers.70.self_attn.k_proj.bias": "model-00071-of-00092.safetensors", + "model.layers.70.self_attn.k_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.self_attn.o_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.self_attn.q_norm.weight": "model-00071-of-00092.safetensors", + "model.layers.70.self_attn.q_proj.bias": "model-00071-of-00092.safetensors", + "model.layers.70.self_attn.q_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.70.self_attn.v_proj.bias": "model-00071-of-00092.safetensors", + "model.layers.70.self_attn.v_proj.weight": "model-00071-of-00092.safetensors", + "model.layers.71.input_layernorm.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.0.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.0.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.0.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.1.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.1.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.1.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.10.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.10.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.10.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.100.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.100.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.100.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.101.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.101.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.101.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.102.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.102.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.102.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.103.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.103.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.103.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.104.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.104.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.104.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.105.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.105.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.105.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.106.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.106.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.106.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.107.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.107.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.107.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.108.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.108.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.108.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.109.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.109.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.109.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.11.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.11.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.11.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.110.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.110.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.110.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.111.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.111.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.111.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.112.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.112.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.112.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.113.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.113.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.113.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.114.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.114.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.114.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.115.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.115.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.115.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.116.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.116.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.116.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.117.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.117.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.117.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.118.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.118.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.118.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.119.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.119.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.119.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.12.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.12.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.12.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.120.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.120.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.120.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.121.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.121.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.121.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.122.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.122.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.122.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.123.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.123.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.123.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.124.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.124.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.124.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.125.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.125.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.125.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.126.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.126.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.126.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.127.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.127.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.127.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.128.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.128.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.128.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.129.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.129.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.129.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.13.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.13.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.13.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.130.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.130.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.130.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.131.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.131.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.131.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.132.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.132.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.132.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.133.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.133.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.133.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.134.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.134.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.134.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.135.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.135.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.135.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.136.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.136.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.136.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.137.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.137.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.137.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.138.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.138.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.138.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.139.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.139.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.139.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.14.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.14.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.14.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.140.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.140.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.140.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.141.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.141.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.141.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.142.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.142.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.142.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.143.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.143.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.143.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.144.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.144.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.144.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.145.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.145.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.145.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.146.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.146.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.146.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.147.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.147.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.147.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.148.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.148.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.148.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.149.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.149.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.149.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.15.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.15.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.15.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.150.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.150.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.150.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.151.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.151.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.151.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.152.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.152.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.152.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.153.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.153.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.153.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.154.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.154.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.154.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.155.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.155.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.155.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.156.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.156.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.156.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.157.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.157.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.157.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.158.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.158.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.158.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.159.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.159.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.159.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.16.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.16.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.16.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.17.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.17.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.17.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.18.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.18.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.18.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.19.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.19.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.19.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.2.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.2.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.2.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.20.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.20.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.20.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.21.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.21.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.21.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.22.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.22.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.22.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.23.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.23.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.23.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.24.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.24.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.24.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.25.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.25.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.25.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.26.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.26.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.26.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.27.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.27.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.27.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.28.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.28.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.28.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.29.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.29.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.29.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.3.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.3.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.3.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.30.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.30.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.30.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.31.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.31.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.31.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.32.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.32.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.32.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.33.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.33.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.33.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.34.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.34.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.34.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.35.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.35.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.35.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.36.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.36.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.36.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.37.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.37.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.37.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.38.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.38.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.38.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.39.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.39.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.39.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.4.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.4.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.4.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.40.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.40.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.40.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.41.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.41.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.41.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.42.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.42.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.42.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.43.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.43.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.43.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.44.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.44.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.44.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.45.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.45.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.45.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.46.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.46.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.46.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.47.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.47.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.47.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.48.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.48.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.48.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.49.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.49.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.49.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.5.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.5.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.5.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.50.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.50.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.50.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.51.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.51.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.51.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.52.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.52.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.52.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.53.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.53.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.53.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.54.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.54.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.54.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.55.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.55.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.55.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.56.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.56.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.56.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.57.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.57.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.57.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.58.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.58.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.58.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.59.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.59.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.59.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.6.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.6.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.6.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.60.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.60.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.60.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.61.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.61.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.61.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.62.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.62.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.62.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.63.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.63.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.63.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.64.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.64.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.64.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.65.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.65.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.65.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.66.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.66.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.66.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.67.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.67.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.67.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.68.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.68.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.68.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.69.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.69.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.69.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.7.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.7.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.7.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.70.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.70.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.70.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.71.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.71.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.71.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.72.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.72.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.72.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.73.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.73.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.73.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.74.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.74.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.74.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.75.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.75.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.75.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.76.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.76.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.76.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.77.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.77.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.77.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.78.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.78.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.78.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.79.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.79.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.79.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.8.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.8.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.8.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.80.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.80.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.80.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.81.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.81.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.81.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.82.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.82.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.82.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.83.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.83.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.83.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.84.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.84.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.84.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.85.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.85.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.85.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.86.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.86.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.86.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.87.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.87.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.87.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.88.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.88.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.88.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.89.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.89.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.89.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.9.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.9.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.9.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.90.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.90.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.90.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.91.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.91.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.91.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.92.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.92.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.92.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.93.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.93.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.93.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.94.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.94.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.94.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.95.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.95.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.95.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.96.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.96.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.96.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.97.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.97.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.97.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.98.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.98.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.98.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.99.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.99.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.experts.99.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.gate.e_score_correction_bias": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.gate.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.shared_experts.down_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.shared_experts.gate_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.mlp.shared_experts.up_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.post_attention_layernorm.weight": "model-00072-of-00092.safetensors", + "model.layers.71.self_attn.k_norm.weight": "model-00072-of-00092.safetensors", + "model.layers.71.self_attn.k_proj.bias": "model-00072-of-00092.safetensors", + "model.layers.71.self_attn.k_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.self_attn.o_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.self_attn.q_norm.weight": "model-00072-of-00092.safetensors", + "model.layers.71.self_attn.q_proj.bias": "model-00072-of-00092.safetensors", + "model.layers.71.self_attn.q_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.71.self_attn.v_proj.bias": "model-00072-of-00092.safetensors", + "model.layers.71.self_attn.v_proj.weight": "model-00072-of-00092.safetensors", + "model.layers.72.input_layernorm.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.0.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.0.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.0.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.1.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.1.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.1.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.10.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.10.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.10.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.100.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.100.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.100.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.101.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.101.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.101.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.102.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.102.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.102.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.103.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.103.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.103.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.104.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.104.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.104.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.105.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.105.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.105.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.106.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.106.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.106.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.107.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.107.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.107.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.108.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.108.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.108.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.109.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.109.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.109.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.11.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.11.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.11.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.110.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.110.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.110.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.111.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.111.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.111.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.112.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.112.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.112.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.113.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.113.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.113.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.114.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.114.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.114.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.115.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.115.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.115.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.116.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.116.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.116.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.117.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.117.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.117.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.118.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.118.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.118.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.119.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.119.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.119.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.12.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.12.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.12.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.120.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.120.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.120.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.121.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.121.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.121.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.122.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.122.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.122.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.123.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.123.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.123.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.124.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.124.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.124.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.125.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.125.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.125.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.126.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.126.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.126.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.127.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.127.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.127.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.128.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.128.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.128.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.129.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.129.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.129.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.13.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.13.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.13.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.130.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.130.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.130.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.131.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.131.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.131.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.132.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.132.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.132.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.133.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.133.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.133.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.134.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.134.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.134.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.135.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.135.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.135.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.136.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.136.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.136.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.137.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.137.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.137.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.138.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.138.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.138.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.139.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.139.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.139.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.14.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.14.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.14.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.140.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.140.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.140.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.141.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.141.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.141.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.142.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.142.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.142.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.143.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.143.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.143.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.144.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.144.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.144.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.145.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.145.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.145.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.146.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.146.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.146.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.147.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.147.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.147.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.148.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.148.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.148.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.149.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.149.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.149.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.15.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.15.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.15.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.150.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.150.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.150.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.151.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.151.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.151.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.152.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.152.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.152.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.153.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.153.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.153.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.154.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.154.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.154.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.155.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.155.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.155.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.156.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.156.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.156.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.157.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.157.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.157.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.158.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.158.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.158.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.159.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.159.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.159.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.16.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.16.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.16.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.17.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.17.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.17.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.18.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.18.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.18.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.19.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.19.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.19.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.2.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.2.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.2.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.20.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.20.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.20.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.21.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.21.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.21.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.22.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.22.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.22.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.23.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.23.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.23.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.24.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.24.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.24.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.25.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.25.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.25.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.26.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.26.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.26.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.27.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.27.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.27.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.28.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.28.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.28.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.29.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.29.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.29.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.3.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.3.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.3.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.30.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.30.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.30.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.31.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.31.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.31.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.32.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.32.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.32.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.33.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.33.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.33.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.34.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.34.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.34.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.35.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.35.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.35.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.36.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.36.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.36.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.37.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.37.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.37.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.38.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.38.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.38.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.39.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.39.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.39.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.4.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.4.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.4.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.40.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.40.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.40.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.41.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.41.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.41.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.42.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.42.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.42.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.43.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.43.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.43.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.44.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.44.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.44.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.45.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.45.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.45.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.46.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.46.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.46.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.47.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.47.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.47.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.48.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.48.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.48.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.49.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.49.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.49.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.5.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.5.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.5.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.50.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.50.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.50.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.51.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.51.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.51.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.52.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.52.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.52.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.53.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.53.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.53.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.54.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.54.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.54.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.55.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.55.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.55.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.56.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.56.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.56.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.57.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.57.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.57.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.58.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.58.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.58.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.59.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.59.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.59.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.6.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.6.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.6.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.60.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.60.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.60.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.61.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.61.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.61.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.62.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.62.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.62.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.63.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.63.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.63.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.64.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.64.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.64.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.65.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.65.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.65.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.66.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.66.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.66.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.67.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.67.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.67.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.68.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.68.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.68.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.69.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.69.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.69.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.7.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.7.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.7.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.70.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.70.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.70.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.71.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.71.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.71.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.72.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.72.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.72.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.73.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.73.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.73.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.74.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.74.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.74.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.75.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.75.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.75.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.76.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.76.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.76.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.77.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.77.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.77.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.78.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.78.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.78.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.79.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.79.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.79.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.8.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.8.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.8.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.80.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.80.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.80.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.81.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.81.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.81.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.82.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.82.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.82.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.83.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.83.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.83.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.84.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.84.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.84.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.85.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.85.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.85.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.86.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.86.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.86.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.87.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.87.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.87.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.88.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.88.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.88.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.89.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.89.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.89.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.9.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.9.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.9.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.90.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.90.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.90.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.91.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.91.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.91.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.92.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.92.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.92.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.93.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.93.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.93.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.94.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.94.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.94.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.95.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.95.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.95.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.96.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.96.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.96.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.97.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.97.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.97.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.98.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.98.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.98.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.99.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.99.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.experts.99.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.gate.e_score_correction_bias": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.gate.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.shared_experts.down_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.shared_experts.gate_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.mlp.shared_experts.up_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.post_attention_layernorm.weight": "model-00073-of-00092.safetensors", + "model.layers.72.self_attn.k_norm.weight": "model-00073-of-00092.safetensors", + "model.layers.72.self_attn.k_proj.bias": "model-00073-of-00092.safetensors", + "model.layers.72.self_attn.k_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.self_attn.o_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.self_attn.q_norm.weight": "model-00073-of-00092.safetensors", + "model.layers.72.self_attn.q_proj.bias": "model-00073-of-00092.safetensors", + "model.layers.72.self_attn.q_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.72.self_attn.v_proj.bias": "model-00073-of-00092.safetensors", + "model.layers.72.self_attn.v_proj.weight": "model-00073-of-00092.safetensors", + "model.layers.73.input_layernorm.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.0.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.0.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.0.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.1.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.1.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.1.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.10.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.10.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.10.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.100.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.100.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.100.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.101.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.101.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.101.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.102.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.102.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.102.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.103.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.103.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.103.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.104.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.104.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.104.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.105.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.105.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.105.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.106.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.106.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.106.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.107.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.107.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.107.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.108.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.108.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.108.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.109.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.109.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.109.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.11.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.11.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.11.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.110.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.110.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.110.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.111.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.111.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.111.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.112.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.112.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.112.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.113.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.113.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.113.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.114.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.114.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.114.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.115.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.115.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.115.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.116.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.116.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.116.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.117.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.117.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.117.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.118.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.118.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.118.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.119.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.119.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.119.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.12.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.12.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.12.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.120.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.120.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.120.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.121.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.121.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.121.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.122.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.122.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.122.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.123.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.123.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.123.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.124.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.124.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.124.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.125.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.125.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.125.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.126.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.126.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.126.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.127.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.127.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.127.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.128.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.128.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.128.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.129.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.129.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.129.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.13.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.13.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.13.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.130.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.130.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.130.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.131.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.131.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.131.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.132.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.132.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.132.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.133.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.133.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.133.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.134.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.134.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.134.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.135.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.135.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.135.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.136.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.136.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.136.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.137.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.137.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.137.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.138.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.138.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.138.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.139.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.139.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.139.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.14.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.14.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.14.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.140.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.140.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.140.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.141.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.141.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.141.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.142.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.142.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.142.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.143.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.143.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.143.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.144.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.144.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.144.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.145.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.145.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.145.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.146.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.146.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.146.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.147.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.147.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.147.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.148.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.148.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.148.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.149.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.149.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.149.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.15.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.15.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.15.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.150.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.150.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.150.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.151.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.151.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.151.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.152.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.152.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.152.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.153.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.153.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.153.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.154.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.154.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.154.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.155.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.155.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.155.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.156.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.156.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.156.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.157.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.157.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.157.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.158.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.158.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.158.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.159.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.159.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.159.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.16.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.16.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.16.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.17.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.17.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.17.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.18.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.18.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.18.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.19.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.19.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.19.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.2.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.2.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.2.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.20.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.20.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.20.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.21.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.21.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.21.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.22.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.22.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.22.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.23.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.23.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.23.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.24.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.24.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.24.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.25.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.25.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.25.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.26.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.26.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.26.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.27.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.27.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.27.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.28.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.28.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.28.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.29.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.29.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.29.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.3.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.3.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.3.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.30.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.30.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.30.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.31.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.31.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.31.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.32.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.32.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.32.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.33.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.33.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.33.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.34.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.34.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.34.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.35.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.35.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.35.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.36.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.36.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.36.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.37.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.37.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.37.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.38.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.38.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.38.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.39.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.39.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.39.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.4.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.4.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.4.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.40.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.40.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.40.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.41.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.41.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.41.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.42.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.42.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.42.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.43.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.43.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.43.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.44.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.44.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.44.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.45.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.45.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.45.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.46.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.46.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.46.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.47.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.47.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.47.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.48.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.48.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.48.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.49.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.49.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.49.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.5.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.5.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.5.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.50.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.50.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.50.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.51.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.51.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.51.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.52.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.52.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.52.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.53.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.53.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.53.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.54.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.54.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.54.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.55.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.55.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.55.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.56.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.56.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.56.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.57.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.57.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.57.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.58.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.58.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.58.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.59.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.59.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.59.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.6.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.6.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.6.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.60.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.60.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.60.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.61.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.61.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.61.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.62.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.62.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.62.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.63.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.63.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.63.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.64.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.64.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.64.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.65.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.65.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.65.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.66.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.66.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.66.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.67.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.67.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.67.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.68.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.68.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.68.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.69.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.69.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.69.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.7.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.7.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.7.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.70.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.70.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.70.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.71.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.71.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.71.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.72.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.72.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.72.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.73.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.73.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.73.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.74.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.74.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.74.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.75.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.75.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.75.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.76.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.76.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.76.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.77.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.77.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.77.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.78.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.78.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.78.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.79.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.79.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.79.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.8.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.8.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.8.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.80.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.80.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.80.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.81.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.81.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.81.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.82.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.82.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.82.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.83.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.83.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.83.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.84.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.84.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.84.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.85.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.85.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.85.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.86.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.86.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.86.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.87.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.87.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.87.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.88.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.88.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.88.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.89.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.89.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.89.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.9.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.9.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.9.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.90.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.90.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.90.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.91.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.91.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.91.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.92.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.92.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.92.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.93.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.93.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.93.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.94.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.94.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.94.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.95.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.95.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.95.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.96.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.96.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.96.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.97.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.97.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.97.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.98.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.98.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.98.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.99.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.99.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.experts.99.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.gate.e_score_correction_bias": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.gate.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.shared_experts.down_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.shared_experts.gate_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.mlp.shared_experts.up_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.post_attention_layernorm.weight": "model-00074-of-00092.safetensors", + "model.layers.73.self_attn.k_norm.weight": "model-00074-of-00092.safetensors", + "model.layers.73.self_attn.k_proj.bias": "model-00074-of-00092.safetensors", + "model.layers.73.self_attn.k_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.self_attn.o_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.self_attn.q_norm.weight": "model-00074-of-00092.safetensors", + "model.layers.73.self_attn.q_proj.bias": "model-00074-of-00092.safetensors", + "model.layers.73.self_attn.q_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.73.self_attn.v_proj.bias": "model-00074-of-00092.safetensors", + "model.layers.73.self_attn.v_proj.weight": "model-00074-of-00092.safetensors", + "model.layers.74.input_layernorm.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.0.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.0.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.0.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.1.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.1.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.1.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.10.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.10.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.10.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.100.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.100.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.100.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.101.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.101.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.101.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.102.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.102.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.102.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.103.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.103.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.103.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.104.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.104.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.104.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.105.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.105.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.105.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.106.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.106.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.106.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.107.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.107.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.107.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.108.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.108.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.108.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.109.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.109.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.109.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.11.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.11.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.11.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.110.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.110.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.110.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.111.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.111.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.111.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.112.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.112.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.112.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.113.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.113.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.113.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.114.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.114.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.114.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.115.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.115.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.115.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.116.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.116.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.116.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.117.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.117.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.117.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.118.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.118.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.118.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.119.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.119.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.119.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.12.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.12.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.12.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.120.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.120.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.120.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.121.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.121.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.121.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.122.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.122.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.122.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.123.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.123.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.123.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.124.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.124.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.124.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.125.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.125.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.125.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.126.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.126.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.126.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.127.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.127.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.127.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.128.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.128.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.128.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.129.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.129.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.129.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.13.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.13.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.13.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.130.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.130.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.130.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.131.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.131.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.131.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.132.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.132.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.132.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.133.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.133.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.133.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.134.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.134.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.134.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.135.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.135.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.135.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.136.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.136.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.136.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.137.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.137.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.137.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.138.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.138.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.138.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.139.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.139.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.139.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.14.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.14.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.14.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.140.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.140.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.140.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.141.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.141.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.141.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.142.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.142.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.142.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.143.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.143.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.143.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.144.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.144.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.144.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.145.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.145.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.145.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.146.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.146.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.146.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.147.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.147.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.147.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.148.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.148.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.148.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.149.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.149.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.149.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.15.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.15.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.15.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.150.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.150.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.150.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.151.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.151.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.151.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.152.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.152.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.152.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.153.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.153.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.153.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.154.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.154.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.154.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.155.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.155.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.155.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.156.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.156.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.156.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.157.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.157.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.157.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.158.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.158.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.158.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.159.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.159.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.159.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.16.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.16.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.16.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.17.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.17.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.17.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.18.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.18.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.18.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.19.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.19.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.19.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.2.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.2.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.2.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.20.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.20.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.20.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.21.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.21.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.21.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.22.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.22.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.22.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.23.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.23.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.23.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.24.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.24.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.24.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.25.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.25.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.25.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.26.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.26.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.26.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.27.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.27.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.27.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.28.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.28.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.28.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.29.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.29.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.29.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.3.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.3.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.3.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.30.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.30.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.30.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.31.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.31.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.31.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.32.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.32.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.32.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.33.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.33.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.33.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.34.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.34.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.34.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.35.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.35.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.35.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.36.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.36.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.36.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.37.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.37.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.37.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.38.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.38.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.38.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.39.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.39.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.39.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.4.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.4.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.4.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.40.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.40.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.40.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.41.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.41.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.41.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.42.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.42.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.42.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.43.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.43.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.43.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.44.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.44.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.44.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.45.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.45.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.45.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.46.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.46.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.46.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.47.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.47.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.47.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.48.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.48.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.48.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.49.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.49.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.49.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.5.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.5.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.5.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.50.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.50.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.50.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.51.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.51.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.51.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.52.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.52.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.52.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.53.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.53.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.53.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.54.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.54.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.54.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.55.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.55.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.55.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.56.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.56.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.56.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.57.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.57.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.57.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.58.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.58.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.58.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.59.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.59.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.59.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.6.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.6.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.6.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.60.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.60.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.60.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.61.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.61.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.61.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.62.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.62.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.62.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.63.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.63.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.63.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.64.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.64.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.64.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.65.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.65.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.65.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.66.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.66.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.66.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.67.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.67.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.67.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.68.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.68.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.68.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.69.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.69.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.69.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.7.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.7.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.7.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.70.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.70.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.70.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.71.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.71.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.71.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.72.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.72.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.72.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.73.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.73.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.73.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.74.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.74.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.74.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.75.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.75.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.75.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.76.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.76.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.76.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.77.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.77.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.77.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.78.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.78.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.78.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.79.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.79.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.79.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.8.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.8.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.8.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.80.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.80.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.80.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.81.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.81.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.81.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.82.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.82.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.82.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.83.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.83.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.83.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.84.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.84.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.84.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.85.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.85.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.85.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.86.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.86.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.86.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.87.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.87.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.87.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.88.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.88.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.88.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.89.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.89.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.89.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.9.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.9.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.9.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.90.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.90.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.90.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.91.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.91.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.91.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.92.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.92.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.92.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.93.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.93.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.93.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.94.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.94.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.94.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.95.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.95.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.95.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.96.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.96.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.96.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.97.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.97.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.97.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.98.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.98.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.98.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.99.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.99.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.experts.99.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.gate.e_score_correction_bias": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.gate.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.shared_experts.down_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.shared_experts.gate_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.mlp.shared_experts.up_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.post_attention_layernorm.weight": "model-00075-of-00092.safetensors", + "model.layers.74.self_attn.k_norm.weight": "model-00075-of-00092.safetensors", + "model.layers.74.self_attn.k_proj.bias": "model-00075-of-00092.safetensors", + "model.layers.74.self_attn.k_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.self_attn.o_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.self_attn.q_norm.weight": "model-00075-of-00092.safetensors", + "model.layers.74.self_attn.q_proj.bias": "model-00075-of-00092.safetensors", + "model.layers.74.self_attn.q_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.74.self_attn.v_proj.bias": "model-00075-of-00092.safetensors", + "model.layers.74.self_attn.v_proj.weight": "model-00075-of-00092.safetensors", + "model.layers.75.input_layernorm.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.0.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.0.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.0.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.1.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.1.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.1.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.10.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.10.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.10.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.100.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.100.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.100.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.101.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.101.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.101.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.102.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.102.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.102.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.103.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.103.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.103.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.104.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.104.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.104.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.105.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.105.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.105.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.106.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.106.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.106.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.107.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.107.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.107.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.108.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.108.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.108.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.109.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.109.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.109.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.11.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.11.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.11.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.110.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.110.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.110.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.111.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.111.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.111.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.112.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.112.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.112.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.113.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.113.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.113.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.114.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.114.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.114.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.115.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.115.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.115.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.116.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.116.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.116.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.117.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.117.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.117.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.118.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.118.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.118.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.119.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.119.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.119.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.12.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.12.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.12.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.120.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.120.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.120.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.121.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.121.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.121.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.122.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.122.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.122.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.123.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.123.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.123.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.124.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.124.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.124.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.125.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.125.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.125.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.126.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.126.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.126.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.127.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.127.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.127.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.128.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.128.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.128.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.129.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.129.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.129.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.13.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.13.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.13.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.130.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.130.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.130.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.131.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.131.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.131.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.132.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.132.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.132.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.133.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.133.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.133.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.134.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.134.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.134.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.135.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.135.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.135.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.136.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.136.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.136.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.137.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.137.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.137.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.138.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.138.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.138.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.139.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.139.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.139.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.14.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.14.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.14.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.140.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.140.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.140.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.141.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.141.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.141.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.142.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.142.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.142.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.143.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.143.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.143.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.144.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.144.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.144.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.145.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.145.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.145.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.146.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.146.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.146.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.147.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.147.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.147.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.148.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.148.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.148.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.149.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.149.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.149.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.15.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.15.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.15.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.150.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.150.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.150.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.151.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.151.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.151.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.152.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.152.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.152.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.153.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.153.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.153.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.154.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.154.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.154.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.155.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.155.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.155.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.156.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.156.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.156.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.157.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.157.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.157.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.158.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.158.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.158.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.159.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.159.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.159.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.16.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.16.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.16.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.17.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.17.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.17.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.18.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.18.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.18.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.19.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.19.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.19.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.2.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.2.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.2.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.20.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.20.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.20.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.21.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.21.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.21.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.22.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.22.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.22.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.23.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.23.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.23.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.24.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.24.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.24.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.25.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.25.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.25.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.26.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.26.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.26.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.27.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.27.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.27.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.28.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.28.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.28.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.29.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.29.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.29.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.3.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.3.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.3.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.30.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.30.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.30.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.31.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.31.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.31.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.32.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.32.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.32.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.33.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.33.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.33.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.34.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.34.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.34.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.35.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.35.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.35.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.36.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.36.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.36.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.37.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.37.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.37.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.38.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.38.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.38.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.39.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.39.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.39.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.4.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.4.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.4.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.40.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.40.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.40.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.41.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.41.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.41.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.42.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.42.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.42.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.43.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.43.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.43.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.44.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.44.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.44.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.45.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.45.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.45.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.46.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.46.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.46.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.47.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.47.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.47.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.48.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.48.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.48.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.49.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.49.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.49.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.5.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.5.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.5.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.50.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.50.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.50.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.51.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.51.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.51.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.52.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.52.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.52.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.53.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.53.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.53.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.54.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.54.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.54.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.55.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.55.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.55.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.56.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.56.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.56.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.57.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.57.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.57.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.58.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.58.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.58.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.59.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.59.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.59.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.6.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.6.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.6.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.60.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.60.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.60.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.61.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.61.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.61.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.62.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.62.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.62.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.63.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.63.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.63.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.64.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.64.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.64.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.65.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.65.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.65.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.66.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.66.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.66.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.67.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.67.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.67.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.68.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.68.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.68.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.69.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.69.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.69.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.7.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.7.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.7.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.70.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.70.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.70.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.71.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.71.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.71.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.72.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.72.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.72.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.73.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.73.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.73.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.74.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.74.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.74.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.75.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.75.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.75.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.76.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.76.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.76.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.77.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.77.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.77.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.78.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.78.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.78.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.79.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.79.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.79.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.8.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.8.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.8.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.80.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.80.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.80.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.81.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.81.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.81.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.82.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.82.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.82.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.83.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.83.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.83.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.84.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.84.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.84.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.85.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.85.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.85.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.86.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.86.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.86.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.87.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.87.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.87.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.88.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.88.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.88.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.89.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.89.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.89.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.9.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.9.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.9.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.90.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.90.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.90.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.91.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.91.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.91.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.92.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.92.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.92.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.93.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.93.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.93.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.94.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.94.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.94.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.95.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.95.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.95.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.96.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.96.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.96.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.97.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.97.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.97.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.98.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.98.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.98.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.99.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.99.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.experts.99.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.gate.e_score_correction_bias": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.gate.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.shared_experts.down_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.shared_experts.gate_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.mlp.shared_experts.up_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.post_attention_layernorm.weight": "model-00076-of-00092.safetensors", + "model.layers.75.self_attn.k_norm.weight": "model-00076-of-00092.safetensors", + "model.layers.75.self_attn.k_proj.bias": "model-00076-of-00092.safetensors", + "model.layers.75.self_attn.k_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.self_attn.o_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.self_attn.q_norm.weight": "model-00076-of-00092.safetensors", + "model.layers.75.self_attn.q_proj.bias": "model-00076-of-00092.safetensors", + "model.layers.75.self_attn.q_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.75.self_attn.v_proj.bias": "model-00076-of-00092.safetensors", + "model.layers.75.self_attn.v_proj.weight": "model-00076-of-00092.safetensors", + "model.layers.76.input_layernorm.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.0.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.0.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.0.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.1.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.1.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.1.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.10.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.10.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.10.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.100.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.100.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.100.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.101.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.101.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.101.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.102.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.102.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.102.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.103.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.103.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.103.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.104.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.104.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.104.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.105.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.105.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.105.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.106.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.106.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.106.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.107.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.107.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.107.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.108.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.108.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.108.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.109.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.109.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.109.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.11.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.11.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.11.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.110.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.110.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.110.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.111.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.111.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.111.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.112.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.112.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.112.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.113.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.113.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.113.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.114.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.114.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.114.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.115.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.115.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.115.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.116.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.116.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.116.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.117.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.117.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.117.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.118.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.118.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.118.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.119.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.119.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.119.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.12.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.12.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.12.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.120.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.120.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.120.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.121.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.121.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.121.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.122.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.122.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.122.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.123.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.123.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.123.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.124.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.124.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.124.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.125.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.125.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.125.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.126.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.126.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.126.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.127.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.127.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.127.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.128.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.128.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.128.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.129.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.129.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.129.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.13.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.13.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.13.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.130.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.130.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.130.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.131.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.131.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.131.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.132.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.132.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.132.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.133.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.133.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.133.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.134.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.134.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.134.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.135.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.135.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.135.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.136.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.136.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.136.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.137.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.137.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.137.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.138.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.138.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.138.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.139.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.139.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.139.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.14.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.14.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.14.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.140.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.140.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.140.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.141.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.141.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.141.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.142.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.142.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.142.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.143.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.143.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.143.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.144.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.144.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.144.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.145.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.145.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.145.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.146.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.146.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.146.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.147.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.147.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.147.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.148.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.148.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.148.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.149.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.149.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.149.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.15.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.15.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.15.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.150.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.150.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.150.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.151.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.151.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.151.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.152.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.152.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.152.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.153.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.153.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.153.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.154.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.154.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.154.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.155.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.155.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.155.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.156.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.156.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.156.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.157.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.157.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.157.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.158.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.158.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.158.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.159.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.159.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.159.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.16.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.16.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.16.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.17.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.17.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.17.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.18.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.18.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.18.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.19.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.19.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.19.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.2.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.2.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.2.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.20.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.20.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.20.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.21.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.21.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.21.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.22.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.22.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.22.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.23.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.23.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.23.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.24.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.24.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.24.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.25.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.25.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.25.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.26.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.26.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.26.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.27.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.27.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.27.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.28.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.28.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.28.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.29.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.29.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.29.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.3.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.3.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.3.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.30.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.30.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.30.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.31.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.31.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.31.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.32.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.32.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.32.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.33.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.33.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.33.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.34.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.34.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.34.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.35.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.35.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.35.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.36.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.36.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.36.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.37.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.37.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.37.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.38.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.38.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.38.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.39.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.39.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.39.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.4.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.4.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.4.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.40.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.40.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.40.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.41.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.41.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.41.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.42.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.42.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.42.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.43.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.43.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.43.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.44.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.44.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.44.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.45.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.45.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.45.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.46.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.46.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.46.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.47.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.47.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.47.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.48.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.48.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.48.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.49.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.49.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.49.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.5.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.5.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.5.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.50.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.50.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.50.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.51.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.51.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.51.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.52.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.52.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.52.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.53.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.53.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.53.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.54.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.54.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.54.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.55.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.55.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.55.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.56.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.56.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.56.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.57.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.57.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.57.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.58.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.58.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.58.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.59.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.59.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.59.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.6.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.6.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.6.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.60.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.60.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.60.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.61.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.61.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.61.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.62.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.62.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.62.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.63.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.63.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.63.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.64.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.64.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.64.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.65.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.65.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.65.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.66.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.66.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.66.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.67.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.67.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.67.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.68.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.68.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.68.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.69.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.69.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.69.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.7.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.7.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.7.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.70.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.70.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.70.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.71.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.71.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.71.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.72.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.72.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.72.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.73.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.73.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.73.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.74.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.74.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.74.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.75.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.75.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.75.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.76.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.76.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.76.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.77.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.77.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.77.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.78.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.78.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.78.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.79.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.79.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.79.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.8.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.8.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.8.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.80.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.80.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.80.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.81.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.81.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.81.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.82.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.82.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.82.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.83.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.83.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.83.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.84.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.84.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.84.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.85.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.85.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.85.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.86.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.86.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.86.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.87.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.87.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.87.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.88.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.88.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.88.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.89.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.89.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.89.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.9.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.9.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.9.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.90.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.90.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.90.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.91.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.91.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.91.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.92.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.92.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.92.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.93.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.93.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.93.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.94.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.94.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.94.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.95.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.95.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.95.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.96.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.96.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.96.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.97.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.97.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.97.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.98.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.98.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.98.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.99.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.99.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.experts.99.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.gate.e_score_correction_bias": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.gate.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.shared_experts.down_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.shared_experts.gate_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.mlp.shared_experts.up_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.post_attention_layernorm.weight": "model-00077-of-00092.safetensors", + "model.layers.76.self_attn.k_norm.weight": "model-00077-of-00092.safetensors", + "model.layers.76.self_attn.k_proj.bias": "model-00077-of-00092.safetensors", + "model.layers.76.self_attn.k_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.self_attn.o_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.self_attn.q_norm.weight": "model-00077-of-00092.safetensors", + "model.layers.76.self_attn.q_proj.bias": "model-00077-of-00092.safetensors", + "model.layers.76.self_attn.q_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.76.self_attn.v_proj.bias": "model-00077-of-00092.safetensors", + "model.layers.76.self_attn.v_proj.weight": "model-00077-of-00092.safetensors", + "model.layers.77.input_layernorm.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.0.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.0.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.0.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.1.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.1.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.1.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.10.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.10.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.10.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.100.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.100.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.100.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.101.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.101.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.101.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.102.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.102.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.102.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.103.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.103.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.103.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.104.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.104.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.104.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.105.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.105.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.105.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.106.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.106.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.106.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.107.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.107.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.107.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.108.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.108.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.108.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.109.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.109.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.109.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.11.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.11.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.11.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.110.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.110.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.110.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.111.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.111.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.111.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.112.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.112.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.112.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.113.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.113.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.113.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.114.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.114.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.114.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.115.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.115.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.115.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.116.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.116.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.116.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.117.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.117.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.117.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.118.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.118.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.118.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.119.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.119.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.119.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.12.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.12.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.12.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.120.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.120.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.120.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.121.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.121.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.121.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.122.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.122.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.122.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.123.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.123.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.123.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.124.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.124.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.124.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.125.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.125.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.125.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.126.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.126.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.126.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.127.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.127.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.127.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.128.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.128.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.128.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.129.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.129.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.129.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.13.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.13.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.13.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.130.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.130.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.130.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.131.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.131.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.131.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.132.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.132.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.132.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.133.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.133.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.133.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.134.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.134.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.134.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.135.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.135.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.135.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.136.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.136.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.136.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.137.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.137.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.137.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.138.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.138.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.138.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.139.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.139.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.139.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.14.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.14.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.14.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.140.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.140.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.140.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.141.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.141.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.141.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.142.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.142.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.142.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.143.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.143.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.143.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.144.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.144.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.144.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.145.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.145.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.145.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.146.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.146.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.146.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.147.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.147.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.147.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.148.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.148.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.148.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.149.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.149.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.149.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.15.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.15.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.15.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.150.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.150.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.150.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.151.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.151.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.151.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.152.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.152.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.152.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.153.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.153.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.153.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.154.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.154.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.154.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.155.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.155.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.155.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.156.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.156.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.156.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.157.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.157.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.157.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.158.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.158.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.158.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.159.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.159.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.159.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.16.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.16.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.16.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.17.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.17.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.17.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.18.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.18.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.18.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.19.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.19.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.19.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.2.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.2.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.2.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.20.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.20.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.20.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.21.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.21.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.21.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.22.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.22.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.22.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.23.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.23.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.23.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.24.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.24.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.24.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.25.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.25.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.25.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.26.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.26.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.26.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.27.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.27.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.27.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.28.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.28.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.28.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.29.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.29.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.29.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.3.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.3.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.3.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.30.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.30.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.30.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.31.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.31.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.31.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.32.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.32.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.32.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.33.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.33.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.33.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.34.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.34.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.34.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.35.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.35.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.35.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.36.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.36.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.36.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.37.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.37.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.37.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.38.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.38.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.38.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.39.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.39.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.39.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.4.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.4.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.4.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.40.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.40.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.40.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.41.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.41.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.41.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.42.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.42.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.42.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.43.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.43.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.43.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.44.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.44.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.44.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.45.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.45.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.45.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.46.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.46.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.46.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.47.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.47.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.47.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.48.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.48.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.48.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.49.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.49.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.49.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.5.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.5.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.5.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.50.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.50.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.50.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.51.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.51.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.51.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.52.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.52.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.52.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.53.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.53.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.53.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.54.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.54.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.54.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.55.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.55.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.55.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.56.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.56.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.56.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.57.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.57.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.57.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.58.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.58.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.58.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.59.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.59.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.59.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.6.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.6.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.6.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.60.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.60.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.60.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.61.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.61.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.61.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.62.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.62.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.62.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.63.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.63.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.63.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.64.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.64.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.64.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.65.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.65.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.65.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.66.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.66.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.66.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.67.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.67.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.67.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.68.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.68.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.68.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.69.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.69.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.69.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.7.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.7.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.7.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.70.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.70.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.70.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.71.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.71.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.71.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.72.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.72.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.72.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.73.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.73.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.73.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.74.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.74.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.74.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.75.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.75.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.75.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.76.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.76.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.76.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.77.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.77.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.77.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.78.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.78.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.78.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.79.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.79.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.79.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.8.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.8.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.8.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.80.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.80.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.80.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.81.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.81.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.81.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.82.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.82.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.82.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.83.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.83.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.83.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.84.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.84.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.84.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.85.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.85.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.85.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.86.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.86.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.86.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.87.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.87.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.87.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.88.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.88.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.88.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.89.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.89.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.89.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.9.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.9.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.9.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.90.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.90.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.90.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.91.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.91.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.91.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.92.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.92.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.92.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.93.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.93.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.93.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.94.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.94.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.94.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.95.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.95.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.95.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.96.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.96.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.96.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.97.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.97.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.97.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.98.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.98.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.98.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.99.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.99.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.experts.99.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.gate.e_score_correction_bias": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.gate.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.shared_experts.down_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.shared_experts.gate_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.mlp.shared_experts.up_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.post_attention_layernorm.weight": "model-00078-of-00092.safetensors", + "model.layers.77.self_attn.k_norm.weight": "model-00078-of-00092.safetensors", + "model.layers.77.self_attn.k_proj.bias": "model-00078-of-00092.safetensors", + "model.layers.77.self_attn.k_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.self_attn.o_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.self_attn.q_norm.weight": "model-00078-of-00092.safetensors", + "model.layers.77.self_attn.q_proj.bias": "model-00078-of-00092.safetensors", + "model.layers.77.self_attn.q_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.77.self_attn.v_proj.bias": "model-00078-of-00092.safetensors", + "model.layers.77.self_attn.v_proj.weight": "model-00078-of-00092.safetensors", + "model.layers.78.input_layernorm.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.0.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.0.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.0.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.1.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.1.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.1.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.10.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.10.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.10.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.100.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.100.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.100.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.101.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.101.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.101.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.102.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.102.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.102.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.103.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.103.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.103.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.104.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.104.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.104.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.105.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.105.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.105.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.106.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.106.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.106.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.107.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.107.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.107.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.108.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.108.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.108.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.109.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.109.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.109.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.11.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.11.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.11.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.110.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.110.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.110.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.111.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.111.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.111.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.112.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.112.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.112.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.113.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.113.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.113.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.114.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.114.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.114.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.115.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.115.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.115.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.116.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.116.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.116.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.117.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.117.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.117.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.118.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.118.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.118.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.119.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.119.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.119.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.12.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.12.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.12.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.120.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.120.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.120.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.121.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.121.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.121.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.122.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.122.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.122.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.123.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.123.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.123.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.124.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.124.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.124.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.125.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.125.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.125.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.126.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.126.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.126.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.127.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.127.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.127.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.128.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.128.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.128.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.129.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.129.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.129.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.13.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.13.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.13.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.130.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.130.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.130.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.131.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.131.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.131.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.132.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.132.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.132.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.133.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.133.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.133.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.134.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.134.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.134.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.135.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.135.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.135.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.136.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.136.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.136.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.137.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.137.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.137.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.138.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.138.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.138.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.139.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.139.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.139.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.14.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.14.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.14.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.140.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.140.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.140.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.141.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.141.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.141.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.142.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.142.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.142.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.143.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.143.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.143.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.144.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.144.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.144.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.145.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.145.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.145.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.146.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.146.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.146.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.147.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.147.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.147.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.148.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.148.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.148.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.149.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.149.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.149.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.15.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.15.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.15.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.150.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.150.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.150.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.151.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.151.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.151.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.152.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.152.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.152.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.153.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.153.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.153.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.154.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.154.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.154.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.155.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.155.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.155.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.156.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.156.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.156.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.157.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.157.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.157.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.158.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.158.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.158.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.159.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.159.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.159.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.16.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.16.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.16.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.17.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.17.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.17.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.18.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.18.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.18.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.19.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.19.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.19.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.2.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.2.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.2.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.20.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.20.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.20.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.21.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.21.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.21.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.22.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.22.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.22.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.23.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.23.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.23.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.24.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.24.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.24.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.25.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.25.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.25.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.26.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.26.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.26.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.27.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.27.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.27.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.28.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.28.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.28.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.29.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.29.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.29.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.3.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.3.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.3.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.30.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.30.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.30.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.31.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.31.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.31.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.32.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.32.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.32.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.33.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.33.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.33.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.34.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.34.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.34.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.35.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.35.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.35.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.36.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.36.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.36.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.37.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.37.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.37.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.38.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.38.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.38.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.39.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.39.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.39.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.4.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.4.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.4.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.40.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.40.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.40.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.41.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.41.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.41.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.42.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.42.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.42.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.43.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.43.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.43.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.44.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.44.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.44.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.45.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.45.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.45.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.46.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.46.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.46.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.47.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.47.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.47.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.48.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.48.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.48.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.49.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.49.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.49.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.5.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.5.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.5.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.50.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.50.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.50.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.51.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.51.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.51.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.52.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.52.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.52.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.53.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.53.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.53.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.54.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.54.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.54.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.55.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.55.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.55.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.56.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.56.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.56.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.57.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.57.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.57.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.58.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.58.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.58.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.59.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.59.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.59.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.6.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.6.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.6.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.60.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.60.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.60.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.61.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.61.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.61.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.62.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.62.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.62.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.63.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.63.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.63.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.64.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.64.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.64.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.65.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.65.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.65.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.66.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.66.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.66.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.67.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.67.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.67.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.68.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.68.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.68.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.69.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.69.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.69.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.7.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.7.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.7.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.70.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.70.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.70.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.71.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.71.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.71.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.72.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.72.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.72.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.73.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.73.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.73.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.74.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.74.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.74.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.75.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.75.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.75.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.76.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.76.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.76.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.77.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.77.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.77.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.78.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.78.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.78.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.79.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.79.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.79.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.8.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.8.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.8.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.80.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.80.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.80.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.81.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.81.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.81.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.82.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.82.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.82.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.83.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.83.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.83.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.84.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.84.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.84.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.85.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.85.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.85.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.86.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.86.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.86.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.87.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.87.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.87.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.88.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.88.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.88.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.89.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.89.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.89.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.9.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.9.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.9.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.90.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.90.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.90.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.91.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.91.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.91.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.92.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.92.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.92.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.93.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.93.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.93.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.94.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.94.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.94.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.95.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.95.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.95.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.96.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.96.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.96.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.97.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.97.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.97.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.98.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.98.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.98.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.99.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.99.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.experts.99.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.gate.e_score_correction_bias": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.gate.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.shared_experts.down_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.shared_experts.gate_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.mlp.shared_experts.up_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.post_attention_layernorm.weight": "model-00079-of-00092.safetensors", + "model.layers.78.self_attn.k_norm.weight": "model-00079-of-00092.safetensors", + "model.layers.78.self_attn.k_proj.bias": "model-00079-of-00092.safetensors", + "model.layers.78.self_attn.k_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.self_attn.o_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.self_attn.q_norm.weight": "model-00079-of-00092.safetensors", + "model.layers.78.self_attn.q_proj.bias": "model-00079-of-00092.safetensors", + "model.layers.78.self_attn.q_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.78.self_attn.v_proj.bias": "model-00079-of-00092.safetensors", + "model.layers.78.self_attn.v_proj.weight": "model-00079-of-00092.safetensors", + "model.layers.79.input_layernorm.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.0.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.0.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.0.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.1.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.1.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.1.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.10.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.10.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.10.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.100.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.100.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.100.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.101.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.101.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.101.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.102.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.102.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.102.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.103.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.103.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.103.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.104.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.104.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.104.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.105.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.105.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.105.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.106.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.106.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.106.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.107.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.107.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.107.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.108.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.108.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.108.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.109.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.109.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.109.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.11.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.11.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.11.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.110.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.110.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.110.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.111.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.111.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.111.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.112.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.112.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.112.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.113.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.113.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.113.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.114.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.114.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.114.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.115.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.115.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.115.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.116.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.116.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.116.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.117.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.117.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.117.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.118.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.118.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.118.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.119.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.119.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.119.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.12.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.12.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.12.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.120.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.120.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.120.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.121.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.121.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.121.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.122.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.122.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.122.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.123.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.123.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.123.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.124.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.124.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.124.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.125.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.125.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.125.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.126.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.126.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.126.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.127.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.127.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.127.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.128.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.128.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.128.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.129.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.129.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.129.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.13.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.13.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.13.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.130.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.130.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.130.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.131.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.131.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.131.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.132.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.132.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.132.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.133.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.133.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.133.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.134.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.134.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.134.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.135.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.135.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.135.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.136.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.136.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.136.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.137.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.137.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.137.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.138.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.138.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.138.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.139.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.139.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.139.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.14.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.14.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.14.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.140.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.140.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.140.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.141.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.141.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.141.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.142.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.142.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.142.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.143.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.143.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.143.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.144.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.144.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.144.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.145.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.145.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.145.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.146.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.146.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.146.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.147.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.147.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.147.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.148.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.148.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.148.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.149.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.149.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.149.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.15.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.15.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.15.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.150.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.150.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.150.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.151.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.151.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.151.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.152.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.152.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.152.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.153.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.153.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.153.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.154.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.154.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.154.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.155.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.155.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.155.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.156.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.156.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.156.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.157.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.157.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.157.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.158.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.158.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.158.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.159.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.159.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.159.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.16.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.16.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.16.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.17.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.17.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.17.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.18.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.18.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.18.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.19.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.19.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.19.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.2.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.2.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.2.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.20.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.20.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.20.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.21.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.21.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.21.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.22.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.22.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.22.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.23.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.23.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.23.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.24.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.24.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.24.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.25.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.25.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.25.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.26.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.26.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.26.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.27.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.27.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.27.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.28.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.28.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.28.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.29.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.29.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.29.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.3.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.3.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.3.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.30.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.30.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.30.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.31.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.31.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.31.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.32.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.32.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.32.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.33.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.33.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.33.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.34.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.34.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.34.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.35.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.35.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.35.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.36.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.36.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.36.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.37.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.37.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.37.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.38.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.38.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.38.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.39.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.39.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.39.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.4.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.4.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.4.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.40.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.40.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.40.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.41.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.41.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.41.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.42.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.42.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.42.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.43.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.43.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.43.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.44.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.44.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.44.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.45.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.45.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.45.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.46.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.46.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.46.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.47.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.47.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.47.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.48.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.48.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.48.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.49.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.49.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.49.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.5.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.5.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.5.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.50.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.50.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.50.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.51.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.51.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.51.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.52.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.52.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.52.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.53.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.53.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.53.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.54.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.54.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.54.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.55.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.55.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.55.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.56.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.56.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.56.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.57.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.57.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.57.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.58.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.58.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.58.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.59.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.59.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.59.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.6.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.6.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.6.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.60.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.60.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.60.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.61.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.61.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.61.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.62.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.62.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.62.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.63.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.63.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.63.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.64.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.64.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.64.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.65.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.65.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.65.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.66.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.66.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.66.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.67.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.67.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.67.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.68.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.68.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.68.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.69.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.69.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.69.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.7.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.7.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.7.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.70.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.70.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.70.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.71.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.71.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.71.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.72.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.72.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.72.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.73.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.73.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.73.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.74.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.74.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.74.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.75.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.75.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.75.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.76.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.76.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.76.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.77.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.77.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.77.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.78.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.78.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.78.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.79.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.79.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.79.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.8.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.8.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.8.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.80.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.80.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.80.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.81.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.81.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.81.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.82.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.82.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.82.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.83.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.83.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.83.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.84.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.84.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.84.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.85.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.85.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.85.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.86.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.86.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.86.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.87.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.87.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.87.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.88.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.88.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.88.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.89.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.89.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.89.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.9.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.9.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.9.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.90.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.90.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.90.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.91.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.91.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.91.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.92.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.92.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.92.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.93.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.93.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.93.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.94.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.94.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.94.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.95.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.95.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.95.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.96.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.96.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.96.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.97.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.97.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.97.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.98.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.98.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.98.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.99.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.99.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.experts.99.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.gate.e_score_correction_bias": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.gate.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.shared_experts.down_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.shared_experts.gate_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.mlp.shared_experts.up_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.post_attention_layernorm.weight": "model-00080-of-00092.safetensors", + "model.layers.79.self_attn.k_norm.weight": "model-00080-of-00092.safetensors", + "model.layers.79.self_attn.k_proj.bias": "model-00080-of-00092.safetensors", + "model.layers.79.self_attn.k_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.self_attn.o_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.self_attn.q_norm.weight": "model-00080-of-00092.safetensors", + "model.layers.79.self_attn.q_proj.bias": "model-00080-of-00092.safetensors", + "model.layers.79.self_attn.q_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.79.self_attn.v_proj.bias": "model-00080-of-00092.safetensors", + "model.layers.79.self_attn.v_proj.weight": "model-00080-of-00092.safetensors", + "model.layers.80.input_layernorm.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.0.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.0.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.0.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.1.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.1.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.1.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.10.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.10.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.10.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.100.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.100.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.100.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.101.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.101.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.101.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.102.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.102.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.102.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.103.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.103.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.103.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.104.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.104.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.104.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.105.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.105.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.105.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.106.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.106.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.106.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.107.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.107.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.107.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.108.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.108.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.108.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.109.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.109.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.109.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.11.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.11.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.11.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.110.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.110.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.110.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.111.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.111.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.111.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.112.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.112.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.112.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.113.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.113.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.113.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.114.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.114.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.114.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.115.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.115.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.115.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.116.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.116.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.116.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.117.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.117.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.117.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.118.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.118.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.118.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.119.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.119.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.119.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.12.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.12.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.12.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.120.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.120.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.120.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.121.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.121.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.121.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.122.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.122.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.122.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.123.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.123.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.123.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.124.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.124.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.124.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.125.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.125.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.125.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.126.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.126.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.126.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.127.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.127.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.127.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.128.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.128.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.128.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.129.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.129.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.129.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.13.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.13.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.13.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.130.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.130.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.130.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.131.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.131.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.131.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.132.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.132.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.132.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.133.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.133.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.133.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.134.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.134.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.134.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.135.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.135.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.135.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.136.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.136.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.136.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.137.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.137.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.137.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.138.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.138.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.138.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.139.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.139.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.139.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.14.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.14.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.14.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.140.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.140.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.140.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.141.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.141.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.141.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.142.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.142.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.142.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.143.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.143.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.143.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.144.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.144.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.144.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.145.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.145.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.145.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.146.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.146.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.146.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.147.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.147.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.147.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.148.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.148.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.148.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.149.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.149.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.149.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.15.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.15.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.15.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.150.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.150.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.150.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.151.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.151.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.151.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.152.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.152.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.152.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.153.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.153.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.153.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.154.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.154.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.154.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.155.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.155.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.155.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.156.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.156.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.156.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.157.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.157.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.157.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.158.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.158.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.158.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.159.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.159.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.159.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.16.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.16.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.16.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.17.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.17.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.17.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.18.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.18.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.18.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.19.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.19.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.19.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.2.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.2.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.2.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.20.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.20.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.20.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.21.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.21.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.21.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.22.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.22.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.22.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.23.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.23.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.23.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.24.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.24.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.24.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.25.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.25.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.25.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.26.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.26.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.26.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.27.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.27.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.27.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.28.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.28.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.28.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.29.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.29.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.29.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.3.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.3.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.3.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.30.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.30.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.30.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.31.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.31.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.31.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.32.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.32.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.32.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.33.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.33.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.33.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.34.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.34.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.34.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.35.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.35.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.35.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.36.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.36.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.36.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.37.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.37.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.37.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.38.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.38.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.38.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.39.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.39.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.39.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.4.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.4.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.4.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.40.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.40.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.40.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.41.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.41.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.41.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.42.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.42.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.42.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.43.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.43.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.43.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.44.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.44.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.44.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.45.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.45.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.45.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.46.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.46.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.46.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.47.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.47.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.47.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.48.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.48.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.48.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.49.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.49.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.49.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.5.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.5.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.5.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.50.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.50.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.50.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.51.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.51.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.51.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.52.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.52.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.52.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.53.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.53.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.53.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.54.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.54.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.54.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.55.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.55.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.55.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.56.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.56.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.56.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.57.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.57.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.57.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.58.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.58.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.58.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.59.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.59.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.59.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.6.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.6.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.6.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.60.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.60.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.60.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.61.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.61.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.61.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.62.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.62.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.62.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.63.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.63.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.63.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.64.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.64.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.64.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.65.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.65.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.65.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.66.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.66.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.66.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.67.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.67.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.67.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.68.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.68.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.68.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.69.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.69.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.69.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.7.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.7.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.7.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.70.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.70.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.70.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.71.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.71.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.71.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.72.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.72.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.72.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.73.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.73.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.73.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.74.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.74.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.74.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.75.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.75.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.75.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.76.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.76.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.76.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.77.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.77.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.77.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.78.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.78.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.78.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.79.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.79.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.79.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.8.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.8.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.8.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.80.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.80.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.80.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.81.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.81.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.81.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.82.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.82.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.82.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.83.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.83.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.83.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.84.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.84.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.84.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.85.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.85.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.85.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.86.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.86.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.86.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.87.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.87.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.87.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.88.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.88.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.88.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.89.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.89.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.89.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.9.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.9.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.9.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.90.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.90.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.90.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.91.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.91.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.91.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.92.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.92.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.92.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.93.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.93.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.93.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.94.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.94.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.94.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.95.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.95.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.95.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.96.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.96.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.96.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.97.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.97.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.97.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.98.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.98.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.98.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.99.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.99.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.experts.99.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.gate.e_score_correction_bias": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.gate.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.shared_experts.down_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.shared_experts.gate_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.mlp.shared_experts.up_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.post_attention_layernorm.weight": "model-00081-of-00092.safetensors", + "model.layers.80.self_attn.k_norm.weight": "model-00081-of-00092.safetensors", + "model.layers.80.self_attn.k_proj.bias": "model-00081-of-00092.safetensors", + "model.layers.80.self_attn.k_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.self_attn.o_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.self_attn.q_norm.weight": "model-00081-of-00092.safetensors", + "model.layers.80.self_attn.q_proj.bias": "model-00081-of-00092.safetensors", + "model.layers.80.self_attn.q_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.80.self_attn.v_proj.bias": "model-00081-of-00092.safetensors", + "model.layers.80.self_attn.v_proj.weight": "model-00081-of-00092.safetensors", + "model.layers.81.input_layernorm.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.0.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.0.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.0.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.1.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.1.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.1.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.10.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.10.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.10.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.100.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.100.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.100.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.101.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.101.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.101.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.102.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.102.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.102.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.103.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.103.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.103.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.104.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.104.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.104.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.105.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.105.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.105.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.106.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.106.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.106.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.107.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.107.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.107.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.108.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.108.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.108.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.109.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.109.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.109.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.11.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.11.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.11.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.110.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.110.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.110.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.111.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.111.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.111.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.112.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.112.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.112.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.113.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.113.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.113.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.114.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.114.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.114.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.115.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.115.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.115.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.116.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.116.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.116.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.117.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.117.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.117.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.118.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.118.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.118.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.119.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.119.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.119.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.12.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.12.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.12.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.120.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.120.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.120.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.121.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.121.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.121.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.122.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.122.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.122.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.123.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.123.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.123.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.124.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.124.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.124.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.125.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.125.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.125.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.126.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.126.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.126.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.127.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.127.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.127.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.128.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.128.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.128.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.129.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.129.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.129.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.13.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.13.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.13.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.130.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.130.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.130.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.131.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.131.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.131.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.132.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.132.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.132.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.133.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.133.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.133.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.134.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.134.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.134.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.135.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.135.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.135.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.136.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.136.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.136.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.137.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.137.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.137.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.138.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.138.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.138.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.139.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.139.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.139.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.14.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.14.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.14.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.140.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.140.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.140.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.141.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.141.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.141.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.142.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.142.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.142.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.143.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.143.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.143.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.144.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.144.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.144.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.145.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.145.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.145.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.146.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.146.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.146.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.147.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.147.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.147.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.148.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.148.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.148.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.149.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.149.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.149.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.15.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.15.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.15.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.150.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.150.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.150.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.151.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.151.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.151.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.152.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.152.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.152.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.153.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.153.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.153.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.154.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.154.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.154.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.155.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.155.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.155.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.156.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.156.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.156.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.157.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.157.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.157.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.158.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.158.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.158.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.159.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.159.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.159.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.16.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.16.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.16.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.17.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.17.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.17.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.18.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.18.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.18.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.19.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.19.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.19.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.2.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.2.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.2.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.20.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.20.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.20.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.21.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.21.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.21.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.22.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.22.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.22.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.23.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.23.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.23.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.24.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.24.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.24.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.25.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.25.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.25.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.26.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.26.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.26.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.27.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.27.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.27.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.28.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.28.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.28.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.29.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.29.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.29.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.3.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.3.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.3.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.30.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.30.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.30.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.31.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.31.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.31.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.32.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.32.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.32.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.33.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.33.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.33.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.34.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.34.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.34.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.35.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.35.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.35.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.36.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.36.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.36.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.37.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.37.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.37.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.38.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.38.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.38.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.39.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.39.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.39.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.4.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.4.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.4.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.40.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.40.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.40.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.41.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.41.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.41.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.42.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.42.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.42.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.43.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.43.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.43.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.44.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.44.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.44.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.45.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.45.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.45.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.46.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.46.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.46.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.47.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.47.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.47.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.48.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.48.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.48.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.49.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.49.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.49.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.5.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.5.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.5.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.50.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.50.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.50.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.51.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.51.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.51.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.52.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.52.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.52.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.53.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.53.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.53.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.54.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.54.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.54.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.55.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.55.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.55.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.56.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.56.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.56.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.57.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.57.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.57.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.58.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.58.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.58.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.59.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.59.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.59.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.6.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.6.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.6.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.60.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.60.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.60.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.61.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.61.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.61.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.62.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.62.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.62.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.63.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.63.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.63.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.64.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.64.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.64.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.65.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.65.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.65.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.66.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.66.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.66.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.67.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.67.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.67.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.68.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.68.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.68.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.69.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.69.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.69.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.7.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.7.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.7.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.70.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.70.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.70.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.71.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.71.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.71.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.72.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.72.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.72.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.73.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.73.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.73.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.74.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.74.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.74.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.75.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.75.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.75.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.76.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.76.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.76.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.77.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.77.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.77.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.78.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.78.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.78.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.79.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.79.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.79.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.8.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.8.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.8.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.80.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.80.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.80.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.81.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.81.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.81.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.82.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.82.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.82.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.83.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.83.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.83.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.84.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.84.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.84.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.85.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.85.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.85.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.86.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.86.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.86.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.87.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.87.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.87.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.88.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.88.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.88.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.89.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.89.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.89.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.9.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.9.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.9.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.90.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.90.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.90.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.91.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.91.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.91.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.92.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.92.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.92.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.93.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.93.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.93.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.94.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.94.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.94.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.95.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.95.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.95.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.96.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.96.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.96.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.97.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.97.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.97.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.98.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.98.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.98.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.99.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.99.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.experts.99.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.gate.e_score_correction_bias": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.gate.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.shared_experts.down_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.shared_experts.gate_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.mlp.shared_experts.up_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.post_attention_layernorm.weight": "model-00082-of-00092.safetensors", + "model.layers.81.self_attn.k_norm.weight": "model-00082-of-00092.safetensors", + "model.layers.81.self_attn.k_proj.bias": "model-00082-of-00092.safetensors", + "model.layers.81.self_attn.k_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.self_attn.o_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.self_attn.q_norm.weight": "model-00082-of-00092.safetensors", + "model.layers.81.self_attn.q_proj.bias": "model-00082-of-00092.safetensors", + "model.layers.81.self_attn.q_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.81.self_attn.v_proj.bias": "model-00082-of-00092.safetensors", + "model.layers.81.self_attn.v_proj.weight": "model-00082-of-00092.safetensors", + "model.layers.82.input_layernorm.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.0.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.0.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.0.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.1.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.1.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.1.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.10.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.10.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.10.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.100.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.100.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.100.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.101.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.101.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.101.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.102.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.102.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.102.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.103.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.103.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.103.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.104.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.104.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.104.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.105.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.105.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.105.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.106.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.106.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.106.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.107.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.107.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.107.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.108.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.108.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.108.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.109.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.109.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.109.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.11.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.11.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.11.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.110.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.110.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.110.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.111.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.111.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.111.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.112.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.112.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.112.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.113.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.113.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.113.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.114.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.114.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.114.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.115.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.115.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.115.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.116.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.116.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.116.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.117.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.117.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.117.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.118.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.118.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.118.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.119.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.119.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.119.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.12.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.12.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.12.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.120.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.120.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.120.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.121.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.121.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.121.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.122.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.122.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.122.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.123.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.123.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.123.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.124.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.124.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.124.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.125.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.125.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.125.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.126.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.126.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.126.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.127.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.127.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.127.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.128.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.128.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.128.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.129.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.129.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.129.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.13.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.13.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.13.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.130.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.130.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.130.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.131.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.131.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.131.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.132.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.132.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.132.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.133.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.133.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.133.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.134.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.134.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.134.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.135.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.135.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.135.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.136.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.136.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.136.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.137.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.137.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.137.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.138.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.138.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.138.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.139.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.139.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.139.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.14.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.14.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.14.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.140.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.140.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.140.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.141.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.141.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.141.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.142.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.142.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.142.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.143.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.143.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.143.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.144.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.144.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.144.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.145.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.145.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.145.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.146.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.146.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.146.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.147.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.147.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.147.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.148.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.148.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.148.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.149.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.149.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.149.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.15.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.15.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.15.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.150.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.150.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.150.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.151.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.151.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.151.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.152.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.152.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.152.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.153.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.153.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.153.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.154.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.154.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.154.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.155.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.155.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.155.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.156.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.156.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.156.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.157.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.157.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.157.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.158.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.158.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.158.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.159.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.159.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.159.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.16.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.16.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.16.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.17.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.17.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.17.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.18.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.18.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.18.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.19.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.19.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.19.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.2.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.2.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.2.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.20.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.20.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.20.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.21.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.21.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.21.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.22.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.22.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.22.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.23.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.23.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.23.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.24.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.24.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.24.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.25.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.25.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.25.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.26.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.26.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.26.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.27.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.27.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.27.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.28.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.28.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.28.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.29.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.29.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.29.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.3.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.3.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.3.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.30.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.30.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.30.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.31.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.31.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.31.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.32.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.32.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.32.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.33.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.33.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.33.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.34.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.34.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.34.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.35.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.35.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.35.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.36.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.36.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.36.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.37.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.37.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.37.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.38.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.38.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.38.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.39.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.39.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.39.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.4.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.4.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.4.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.40.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.40.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.40.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.41.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.41.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.41.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.42.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.42.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.42.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.43.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.43.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.43.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.44.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.44.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.44.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.45.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.45.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.45.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.46.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.46.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.46.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.47.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.47.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.47.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.48.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.48.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.48.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.49.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.49.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.49.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.5.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.5.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.5.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.50.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.50.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.50.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.51.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.51.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.51.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.52.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.52.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.52.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.53.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.53.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.53.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.54.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.54.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.54.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.55.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.55.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.55.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.56.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.56.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.56.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.57.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.57.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.57.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.58.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.58.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.58.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.59.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.59.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.59.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.6.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.6.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.6.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.60.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.60.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.60.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.61.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.61.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.61.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.62.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.62.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.62.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.63.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.63.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.63.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.64.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.64.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.64.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.65.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.65.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.65.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.66.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.66.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.66.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.67.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.67.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.67.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.68.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.68.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.68.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.69.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.69.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.69.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.7.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.7.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.7.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.70.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.70.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.70.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.71.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.71.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.71.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.72.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.72.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.72.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.73.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.73.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.73.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.74.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.74.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.74.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.75.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.75.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.75.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.76.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.76.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.76.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.77.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.77.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.77.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.78.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.78.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.78.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.79.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.79.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.79.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.8.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.8.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.8.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.80.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.80.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.80.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.81.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.81.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.81.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.82.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.82.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.82.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.83.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.83.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.83.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.84.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.84.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.84.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.85.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.85.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.85.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.86.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.86.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.86.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.87.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.87.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.87.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.88.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.88.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.88.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.89.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.89.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.89.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.9.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.9.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.9.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.90.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.90.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.90.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.91.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.91.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.91.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.92.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.92.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.92.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.93.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.93.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.93.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.94.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.94.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.94.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.95.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.95.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.95.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.96.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.96.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.96.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.97.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.97.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.97.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.98.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.98.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.98.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.99.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.99.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.experts.99.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.gate.e_score_correction_bias": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.gate.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.shared_experts.down_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.shared_experts.gate_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.mlp.shared_experts.up_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.post_attention_layernorm.weight": "model-00083-of-00092.safetensors", + "model.layers.82.self_attn.k_norm.weight": "model-00083-of-00092.safetensors", + "model.layers.82.self_attn.k_proj.bias": "model-00083-of-00092.safetensors", + "model.layers.82.self_attn.k_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.self_attn.o_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.self_attn.q_norm.weight": "model-00083-of-00092.safetensors", + "model.layers.82.self_attn.q_proj.bias": "model-00083-of-00092.safetensors", + "model.layers.82.self_attn.q_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.82.self_attn.v_proj.bias": "model-00083-of-00092.safetensors", + "model.layers.82.self_attn.v_proj.weight": "model-00083-of-00092.safetensors", + "model.layers.83.input_layernorm.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.0.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.0.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.0.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.1.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.1.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.1.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.10.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.10.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.10.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.100.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.100.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.100.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.101.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.101.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.101.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.102.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.102.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.102.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.103.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.103.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.103.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.104.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.104.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.104.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.105.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.105.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.105.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.106.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.106.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.106.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.107.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.107.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.107.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.108.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.108.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.108.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.109.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.109.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.109.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.11.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.11.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.11.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.110.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.110.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.110.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.111.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.111.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.111.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.112.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.112.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.112.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.113.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.113.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.113.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.114.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.114.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.114.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.115.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.115.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.115.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.116.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.116.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.116.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.117.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.117.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.117.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.118.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.118.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.118.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.119.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.119.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.119.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.12.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.12.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.12.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.120.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.120.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.120.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.121.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.121.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.121.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.122.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.122.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.122.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.123.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.123.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.123.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.124.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.124.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.124.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.125.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.125.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.125.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.126.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.126.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.126.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.127.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.127.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.127.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.128.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.128.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.128.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.129.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.129.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.129.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.13.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.13.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.13.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.130.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.130.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.130.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.131.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.131.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.131.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.132.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.132.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.132.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.133.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.133.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.133.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.134.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.134.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.134.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.135.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.135.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.135.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.136.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.136.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.136.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.137.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.137.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.137.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.138.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.138.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.138.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.139.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.139.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.139.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.14.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.14.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.14.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.140.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.140.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.140.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.141.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.141.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.141.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.142.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.142.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.142.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.143.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.143.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.143.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.144.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.144.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.144.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.145.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.145.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.145.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.146.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.146.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.146.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.147.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.147.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.147.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.148.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.148.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.148.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.149.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.149.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.149.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.15.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.15.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.15.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.150.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.150.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.150.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.151.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.151.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.151.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.152.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.152.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.152.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.153.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.153.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.153.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.154.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.154.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.154.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.155.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.155.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.155.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.156.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.156.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.156.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.157.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.157.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.157.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.158.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.158.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.158.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.159.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.159.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.159.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.16.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.16.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.16.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.17.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.17.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.17.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.18.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.18.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.18.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.19.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.19.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.19.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.2.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.2.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.2.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.20.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.20.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.20.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.21.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.21.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.21.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.22.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.22.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.22.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.23.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.23.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.23.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.24.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.24.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.24.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.25.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.25.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.25.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.26.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.26.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.26.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.27.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.27.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.27.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.28.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.28.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.28.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.29.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.29.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.29.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.3.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.3.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.3.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.30.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.30.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.30.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.31.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.31.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.31.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.32.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.32.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.32.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.33.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.33.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.33.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.34.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.34.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.34.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.35.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.35.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.35.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.36.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.36.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.36.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.37.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.37.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.37.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.38.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.38.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.38.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.39.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.39.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.39.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.4.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.4.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.4.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.40.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.40.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.40.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.41.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.41.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.41.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.42.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.42.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.42.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.43.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.43.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.43.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.44.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.44.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.44.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.45.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.45.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.45.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.46.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.46.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.46.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.47.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.47.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.47.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.48.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.48.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.48.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.49.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.49.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.49.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.5.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.5.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.5.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.50.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.50.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.50.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.51.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.51.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.51.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.52.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.52.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.52.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.53.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.53.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.53.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.54.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.54.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.54.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.55.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.55.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.55.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.56.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.56.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.56.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.57.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.57.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.57.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.58.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.58.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.58.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.59.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.59.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.59.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.6.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.6.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.6.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.60.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.60.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.60.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.61.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.61.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.61.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.62.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.62.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.62.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.63.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.63.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.63.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.64.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.64.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.64.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.65.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.65.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.65.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.66.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.66.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.66.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.67.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.67.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.67.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.68.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.68.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.68.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.69.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.69.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.69.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.7.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.7.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.7.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.70.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.70.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.70.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.71.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.71.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.71.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.72.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.72.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.72.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.73.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.73.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.73.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.74.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.74.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.74.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.75.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.75.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.75.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.76.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.76.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.76.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.77.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.77.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.77.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.78.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.78.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.78.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.79.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.79.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.79.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.8.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.8.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.8.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.80.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.80.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.80.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.81.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.81.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.81.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.82.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.82.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.82.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.83.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.83.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.83.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.84.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.84.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.84.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.85.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.85.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.85.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.86.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.86.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.86.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.87.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.87.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.87.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.88.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.88.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.88.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.89.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.89.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.89.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.9.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.9.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.9.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.90.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.90.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.90.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.91.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.91.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.91.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.92.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.92.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.92.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.93.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.93.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.93.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.94.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.94.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.94.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.95.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.95.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.95.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.96.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.96.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.96.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.97.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.97.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.97.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.98.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.98.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.98.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.99.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.99.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.experts.99.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.gate.e_score_correction_bias": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.gate.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.shared_experts.down_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.shared_experts.gate_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.mlp.shared_experts.up_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.post_attention_layernorm.weight": "model-00084-of-00092.safetensors", + "model.layers.83.self_attn.k_norm.weight": "model-00084-of-00092.safetensors", + "model.layers.83.self_attn.k_proj.bias": "model-00084-of-00092.safetensors", + "model.layers.83.self_attn.k_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.self_attn.o_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.self_attn.q_norm.weight": "model-00084-of-00092.safetensors", + "model.layers.83.self_attn.q_proj.bias": "model-00084-of-00092.safetensors", + "model.layers.83.self_attn.q_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.83.self_attn.v_proj.bias": "model-00084-of-00092.safetensors", + "model.layers.83.self_attn.v_proj.weight": "model-00084-of-00092.safetensors", + "model.layers.84.input_layernorm.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.0.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.0.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.0.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.1.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.1.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.1.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.10.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.10.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.10.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.100.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.100.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.100.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.101.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.101.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.101.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.102.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.102.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.102.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.103.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.103.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.103.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.104.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.104.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.104.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.105.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.105.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.105.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.106.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.106.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.106.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.107.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.107.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.107.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.108.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.108.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.108.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.109.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.109.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.109.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.11.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.11.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.11.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.110.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.110.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.110.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.111.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.111.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.111.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.112.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.112.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.112.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.113.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.113.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.113.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.114.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.114.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.114.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.115.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.115.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.115.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.116.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.116.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.116.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.117.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.117.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.117.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.118.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.118.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.118.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.119.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.119.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.119.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.12.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.12.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.12.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.120.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.120.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.120.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.121.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.121.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.121.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.122.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.122.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.122.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.123.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.123.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.123.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.124.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.124.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.124.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.125.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.125.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.125.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.126.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.126.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.126.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.127.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.127.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.127.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.128.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.128.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.128.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.129.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.129.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.129.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.13.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.13.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.13.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.130.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.130.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.130.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.131.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.131.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.131.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.132.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.132.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.132.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.133.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.133.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.133.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.134.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.134.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.134.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.135.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.135.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.135.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.136.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.136.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.136.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.137.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.137.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.137.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.138.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.138.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.138.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.139.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.139.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.139.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.14.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.14.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.14.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.140.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.140.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.140.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.141.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.141.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.141.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.142.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.142.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.142.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.143.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.143.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.143.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.144.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.144.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.144.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.145.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.145.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.145.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.146.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.146.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.146.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.147.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.147.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.147.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.148.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.148.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.148.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.149.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.149.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.149.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.15.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.15.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.15.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.150.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.150.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.150.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.151.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.151.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.151.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.152.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.152.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.152.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.153.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.153.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.153.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.154.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.154.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.154.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.155.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.155.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.155.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.156.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.156.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.156.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.157.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.157.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.157.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.158.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.158.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.158.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.159.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.159.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.159.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.16.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.16.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.16.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.17.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.17.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.17.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.18.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.18.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.18.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.19.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.19.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.19.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.2.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.2.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.2.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.20.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.20.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.20.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.21.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.21.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.21.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.22.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.22.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.22.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.23.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.23.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.23.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.24.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.24.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.24.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.25.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.25.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.25.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.26.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.26.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.26.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.27.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.27.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.27.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.28.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.28.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.28.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.29.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.29.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.29.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.3.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.3.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.3.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.30.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.30.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.30.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.31.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.31.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.31.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.32.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.32.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.32.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.33.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.33.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.33.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.34.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.34.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.34.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.35.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.35.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.35.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.36.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.36.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.36.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.37.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.37.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.37.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.38.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.38.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.38.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.39.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.39.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.39.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.4.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.4.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.4.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.40.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.40.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.40.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.41.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.41.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.41.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.42.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.42.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.42.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.43.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.43.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.43.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.44.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.44.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.44.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.45.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.45.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.45.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.46.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.46.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.46.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.47.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.47.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.47.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.48.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.48.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.48.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.49.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.49.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.49.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.5.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.5.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.5.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.50.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.50.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.50.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.51.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.51.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.51.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.52.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.52.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.52.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.53.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.53.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.53.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.54.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.54.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.54.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.55.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.55.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.55.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.56.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.56.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.56.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.57.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.57.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.57.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.58.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.58.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.58.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.59.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.59.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.59.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.6.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.6.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.6.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.60.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.60.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.60.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.61.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.61.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.61.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.62.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.62.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.62.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.63.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.63.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.63.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.64.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.64.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.64.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.65.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.65.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.65.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.66.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.66.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.66.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.67.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.67.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.67.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.68.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.68.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.68.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.69.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.69.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.69.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.7.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.7.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.7.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.70.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.70.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.70.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.71.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.71.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.71.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.72.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.72.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.72.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.73.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.73.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.73.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.74.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.74.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.74.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.75.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.75.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.75.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.76.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.76.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.76.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.77.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.77.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.77.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.78.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.78.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.78.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.79.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.79.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.79.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.8.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.8.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.8.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.80.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.80.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.80.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.81.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.81.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.81.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.82.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.82.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.82.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.83.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.83.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.83.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.84.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.84.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.84.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.85.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.85.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.85.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.86.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.86.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.86.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.87.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.87.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.87.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.88.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.88.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.88.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.89.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.89.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.89.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.9.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.9.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.9.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.90.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.90.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.90.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.91.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.91.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.91.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.92.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.92.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.92.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.93.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.93.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.93.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.94.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.94.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.94.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.95.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.95.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.95.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.96.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.96.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.96.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.97.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.97.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.97.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.98.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.98.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.98.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.99.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.99.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.experts.99.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.gate.e_score_correction_bias": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.gate.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.shared_experts.down_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.shared_experts.gate_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.mlp.shared_experts.up_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.post_attention_layernorm.weight": "model-00085-of-00092.safetensors", + "model.layers.84.self_attn.k_norm.weight": "model-00085-of-00092.safetensors", + "model.layers.84.self_attn.k_proj.bias": "model-00085-of-00092.safetensors", + "model.layers.84.self_attn.k_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.self_attn.o_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.self_attn.q_norm.weight": "model-00085-of-00092.safetensors", + "model.layers.84.self_attn.q_proj.bias": "model-00085-of-00092.safetensors", + "model.layers.84.self_attn.q_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.84.self_attn.v_proj.bias": "model-00085-of-00092.safetensors", + "model.layers.84.self_attn.v_proj.weight": "model-00085-of-00092.safetensors", + "model.layers.85.input_layernorm.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.0.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.0.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.0.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.1.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.1.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.1.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.10.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.10.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.10.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.100.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.100.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.100.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.101.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.101.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.101.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.102.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.102.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.102.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.103.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.103.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.103.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.104.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.104.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.104.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.105.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.105.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.105.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.106.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.106.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.106.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.107.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.107.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.107.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.108.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.108.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.108.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.109.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.109.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.109.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.11.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.11.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.11.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.110.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.110.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.110.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.111.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.111.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.111.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.112.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.112.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.112.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.113.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.113.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.113.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.114.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.114.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.114.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.115.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.115.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.115.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.116.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.116.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.116.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.117.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.117.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.117.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.118.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.118.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.118.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.119.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.119.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.119.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.12.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.12.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.12.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.120.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.120.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.120.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.121.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.121.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.121.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.122.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.122.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.122.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.123.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.123.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.123.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.124.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.124.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.124.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.125.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.125.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.125.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.126.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.126.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.126.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.127.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.127.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.127.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.128.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.128.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.128.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.129.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.129.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.129.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.13.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.13.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.13.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.130.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.130.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.130.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.131.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.131.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.131.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.132.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.132.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.132.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.133.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.133.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.133.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.134.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.134.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.134.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.135.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.135.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.135.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.136.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.136.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.136.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.137.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.137.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.137.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.138.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.138.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.138.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.139.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.139.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.139.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.14.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.14.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.14.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.140.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.140.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.140.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.141.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.141.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.141.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.142.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.142.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.142.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.143.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.143.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.143.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.144.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.144.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.144.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.145.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.145.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.145.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.146.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.146.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.146.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.147.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.147.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.147.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.148.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.148.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.148.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.149.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.149.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.149.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.15.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.15.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.15.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.150.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.150.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.150.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.151.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.151.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.151.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.152.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.152.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.152.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.153.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.153.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.153.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.154.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.154.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.154.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.155.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.155.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.155.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.156.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.156.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.156.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.157.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.157.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.157.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.158.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.158.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.158.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.159.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.159.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.159.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.16.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.16.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.16.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.17.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.17.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.17.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.18.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.18.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.18.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.19.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.19.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.19.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.2.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.2.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.2.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.20.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.20.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.20.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.21.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.21.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.21.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.22.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.22.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.22.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.23.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.23.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.23.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.24.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.24.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.24.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.25.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.25.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.25.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.26.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.26.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.26.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.27.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.27.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.27.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.28.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.28.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.28.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.29.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.29.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.29.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.3.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.3.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.3.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.30.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.30.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.30.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.31.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.31.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.31.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.32.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.32.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.32.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.33.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.33.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.33.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.34.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.34.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.34.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.35.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.35.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.35.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.36.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.36.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.36.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.37.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.37.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.37.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.38.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.38.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.38.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.39.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.39.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.39.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.4.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.4.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.4.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.40.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.40.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.40.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.41.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.41.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.41.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.42.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.42.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.42.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.43.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.43.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.43.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.44.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.44.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.44.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.45.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.45.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.45.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.46.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.46.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.46.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.47.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.47.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.47.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.48.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.48.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.48.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.49.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.49.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.49.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.5.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.5.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.5.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.50.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.50.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.50.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.51.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.51.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.51.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.52.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.52.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.52.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.53.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.53.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.53.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.54.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.54.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.54.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.55.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.55.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.55.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.56.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.56.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.56.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.57.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.57.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.57.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.58.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.58.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.58.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.59.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.59.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.59.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.6.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.6.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.6.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.60.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.60.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.60.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.61.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.61.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.61.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.62.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.62.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.62.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.63.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.63.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.63.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.64.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.64.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.64.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.65.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.65.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.65.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.66.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.66.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.66.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.67.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.67.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.67.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.68.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.68.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.68.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.69.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.69.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.69.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.7.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.7.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.7.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.70.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.70.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.70.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.71.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.71.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.71.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.72.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.72.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.72.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.73.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.73.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.73.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.74.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.74.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.74.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.75.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.75.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.75.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.76.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.76.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.76.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.77.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.77.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.77.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.78.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.78.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.78.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.79.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.79.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.79.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.8.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.8.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.8.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.80.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.80.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.80.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.81.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.81.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.81.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.82.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.82.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.82.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.83.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.83.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.83.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.84.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.84.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.84.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.85.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.85.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.85.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.86.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.86.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.86.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.87.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.87.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.87.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.88.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.88.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.88.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.89.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.89.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.89.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.9.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.9.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.9.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.90.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.90.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.90.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.91.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.91.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.91.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.92.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.92.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.92.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.93.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.93.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.93.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.94.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.94.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.94.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.95.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.95.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.95.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.96.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.96.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.96.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.97.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.97.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.97.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.98.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.98.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.98.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.99.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.99.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.experts.99.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.gate.e_score_correction_bias": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.gate.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.shared_experts.down_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.shared_experts.gate_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.mlp.shared_experts.up_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.post_attention_layernorm.weight": "model-00086-of-00092.safetensors", + "model.layers.85.self_attn.k_norm.weight": "model-00086-of-00092.safetensors", + "model.layers.85.self_attn.k_proj.bias": "model-00086-of-00092.safetensors", + "model.layers.85.self_attn.k_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.self_attn.o_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.self_attn.q_norm.weight": "model-00086-of-00092.safetensors", + "model.layers.85.self_attn.q_proj.bias": "model-00086-of-00092.safetensors", + "model.layers.85.self_attn.q_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.85.self_attn.v_proj.bias": "model-00086-of-00092.safetensors", + "model.layers.85.self_attn.v_proj.weight": "model-00086-of-00092.safetensors", + "model.layers.86.input_layernorm.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.0.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.0.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.0.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.1.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.1.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.1.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.10.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.10.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.10.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.100.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.100.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.100.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.101.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.101.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.101.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.102.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.102.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.102.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.103.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.103.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.103.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.104.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.104.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.104.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.105.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.105.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.105.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.106.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.106.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.106.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.107.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.107.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.107.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.108.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.108.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.108.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.109.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.109.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.109.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.11.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.11.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.11.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.110.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.110.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.110.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.111.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.111.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.111.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.112.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.112.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.112.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.113.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.113.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.113.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.114.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.114.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.114.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.115.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.115.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.115.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.116.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.116.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.116.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.117.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.117.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.117.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.118.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.118.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.118.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.119.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.119.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.119.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.12.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.12.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.12.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.120.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.120.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.120.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.121.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.121.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.121.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.122.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.122.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.122.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.123.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.123.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.123.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.124.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.124.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.124.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.125.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.125.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.125.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.126.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.126.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.126.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.127.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.127.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.127.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.128.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.128.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.128.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.129.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.129.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.129.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.13.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.13.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.13.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.130.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.130.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.130.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.131.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.131.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.131.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.132.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.132.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.132.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.133.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.133.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.133.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.134.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.134.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.134.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.135.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.135.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.135.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.136.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.136.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.136.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.137.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.137.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.137.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.138.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.138.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.138.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.139.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.139.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.139.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.14.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.14.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.14.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.140.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.140.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.140.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.141.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.141.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.141.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.142.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.142.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.142.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.143.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.143.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.143.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.144.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.144.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.144.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.145.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.145.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.145.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.146.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.146.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.146.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.147.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.147.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.147.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.148.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.148.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.148.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.149.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.149.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.149.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.15.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.15.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.15.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.150.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.150.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.150.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.151.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.151.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.151.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.152.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.152.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.152.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.153.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.153.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.153.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.154.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.154.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.154.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.155.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.155.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.155.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.156.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.156.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.156.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.157.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.157.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.157.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.158.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.158.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.158.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.159.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.159.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.159.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.16.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.16.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.16.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.17.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.17.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.17.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.18.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.18.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.18.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.19.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.19.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.19.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.2.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.2.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.2.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.20.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.20.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.20.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.21.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.21.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.21.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.22.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.22.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.22.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.23.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.23.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.23.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.24.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.24.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.24.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.25.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.25.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.25.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.26.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.26.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.26.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.27.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.27.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.27.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.28.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.28.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.28.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.29.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.29.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.29.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.3.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.3.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.3.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.30.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.30.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.30.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.31.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.31.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.31.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.32.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.32.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.32.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.33.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.33.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.33.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.34.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.34.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.34.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.35.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.35.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.35.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.36.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.36.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.36.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.37.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.37.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.37.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.38.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.38.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.38.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.39.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.39.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.39.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.4.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.4.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.4.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.40.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.40.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.40.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.41.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.41.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.41.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.42.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.42.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.42.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.43.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.43.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.43.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.44.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.44.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.44.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.45.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.45.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.45.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.46.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.46.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.46.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.47.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.47.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.47.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.48.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.48.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.48.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.49.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.49.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.49.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.5.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.5.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.5.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.50.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.50.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.50.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.51.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.51.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.51.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.52.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.52.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.52.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.53.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.53.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.53.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.54.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.54.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.54.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.55.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.55.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.55.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.56.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.56.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.56.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.57.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.57.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.57.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.58.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.58.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.58.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.59.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.59.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.59.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.6.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.6.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.6.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.60.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.60.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.60.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.61.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.61.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.61.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.62.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.62.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.62.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.63.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.63.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.63.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.64.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.64.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.64.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.65.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.65.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.65.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.66.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.66.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.66.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.67.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.67.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.67.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.68.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.68.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.68.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.69.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.69.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.69.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.7.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.7.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.7.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.70.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.70.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.70.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.71.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.71.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.71.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.72.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.72.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.72.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.73.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.73.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.73.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.74.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.74.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.74.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.75.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.75.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.75.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.76.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.76.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.76.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.77.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.77.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.77.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.78.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.78.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.78.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.79.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.79.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.79.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.8.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.8.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.8.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.80.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.80.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.80.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.81.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.81.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.81.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.82.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.82.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.82.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.83.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.83.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.83.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.84.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.84.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.84.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.85.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.85.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.85.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.86.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.86.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.86.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.87.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.87.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.87.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.88.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.88.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.88.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.89.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.89.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.89.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.9.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.9.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.9.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.90.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.90.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.90.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.91.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.91.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.91.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.92.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.92.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.92.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.93.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.93.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.93.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.94.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.94.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.94.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.95.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.95.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.95.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.96.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.96.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.96.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.97.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.97.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.97.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.98.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.98.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.98.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.99.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.99.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.experts.99.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.gate.e_score_correction_bias": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.gate.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.shared_experts.down_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.shared_experts.gate_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.mlp.shared_experts.up_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.post_attention_layernorm.weight": "model-00087-of-00092.safetensors", + "model.layers.86.self_attn.k_norm.weight": "model-00087-of-00092.safetensors", + "model.layers.86.self_attn.k_proj.bias": "model-00087-of-00092.safetensors", + "model.layers.86.self_attn.k_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.self_attn.o_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.self_attn.q_norm.weight": "model-00087-of-00092.safetensors", + "model.layers.86.self_attn.q_proj.bias": "model-00087-of-00092.safetensors", + "model.layers.86.self_attn.q_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.86.self_attn.v_proj.bias": "model-00087-of-00092.safetensors", + "model.layers.86.self_attn.v_proj.weight": "model-00087-of-00092.safetensors", + "model.layers.87.input_layernorm.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.0.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.0.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.0.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.1.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.1.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.1.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.10.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.10.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.10.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.100.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.100.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.100.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.101.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.101.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.101.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.102.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.102.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.102.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.103.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.103.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.103.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.104.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.104.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.104.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.105.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.105.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.105.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.106.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.106.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.106.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.107.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.107.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.107.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.108.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.108.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.108.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.109.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.109.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.109.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.11.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.11.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.11.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.110.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.110.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.110.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.111.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.111.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.111.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.112.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.112.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.112.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.113.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.113.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.113.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.114.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.114.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.114.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.115.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.115.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.115.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.116.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.116.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.116.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.117.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.117.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.117.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.118.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.118.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.118.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.119.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.119.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.119.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.12.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.12.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.12.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.120.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.120.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.120.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.121.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.121.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.121.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.122.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.122.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.122.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.123.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.123.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.123.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.124.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.124.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.124.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.125.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.125.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.125.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.126.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.126.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.126.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.127.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.127.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.127.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.128.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.128.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.128.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.129.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.129.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.129.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.13.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.13.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.13.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.130.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.130.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.130.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.131.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.131.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.131.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.132.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.132.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.132.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.133.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.133.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.133.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.134.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.134.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.134.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.135.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.135.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.135.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.136.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.136.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.136.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.137.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.137.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.137.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.138.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.138.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.138.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.139.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.139.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.139.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.14.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.14.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.14.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.140.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.140.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.140.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.141.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.141.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.141.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.142.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.142.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.142.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.143.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.143.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.143.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.144.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.144.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.144.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.145.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.145.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.145.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.146.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.146.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.146.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.147.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.147.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.147.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.148.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.148.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.148.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.149.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.149.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.149.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.15.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.15.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.15.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.150.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.150.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.150.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.151.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.151.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.151.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.152.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.152.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.152.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.153.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.153.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.153.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.154.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.154.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.154.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.155.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.155.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.155.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.156.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.156.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.156.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.157.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.157.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.157.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.158.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.158.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.158.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.159.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.159.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.159.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.16.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.16.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.16.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.17.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.17.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.17.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.18.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.18.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.18.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.19.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.19.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.19.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.2.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.2.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.2.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.20.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.20.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.20.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.21.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.21.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.21.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.22.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.22.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.22.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.23.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.23.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.23.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.24.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.24.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.24.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.25.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.25.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.25.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.26.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.26.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.26.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.27.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.27.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.27.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.28.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.28.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.28.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.29.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.29.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.29.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.3.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.3.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.3.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.30.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.30.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.30.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.31.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.31.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.31.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.32.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.32.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.32.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.33.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.33.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.33.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.34.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.34.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.34.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.35.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.35.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.35.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.36.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.36.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.36.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.37.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.37.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.37.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.38.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.38.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.38.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.39.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.39.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.39.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.4.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.4.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.4.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.40.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.40.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.40.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.41.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.41.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.41.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.42.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.42.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.42.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.43.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.43.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.43.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.44.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.44.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.44.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.45.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.45.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.45.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.46.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.46.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.46.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.47.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.47.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.47.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.48.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.48.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.48.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.49.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.49.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.49.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.5.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.5.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.5.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.50.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.50.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.50.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.51.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.51.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.51.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.52.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.52.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.52.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.53.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.53.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.53.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.54.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.54.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.54.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.55.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.55.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.55.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.56.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.56.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.56.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.57.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.57.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.57.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.58.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.58.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.58.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.59.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.59.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.59.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.6.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.6.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.6.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.60.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.60.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.60.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.61.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.61.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.61.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.62.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.62.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.62.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.63.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.63.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.63.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.64.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.64.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.64.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.65.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.65.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.65.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.66.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.66.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.66.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.67.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.67.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.67.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.68.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.68.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.68.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.69.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.69.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.69.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.7.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.7.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.7.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.70.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.70.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.70.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.71.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.71.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.71.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.72.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.72.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.72.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.73.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.73.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.73.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.74.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.74.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.74.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.75.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.75.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.75.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.76.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.76.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.76.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.77.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.77.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.77.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.78.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.78.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.78.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.79.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.79.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.79.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.8.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.8.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.8.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.80.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.80.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.80.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.81.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.81.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.81.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.82.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.82.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.82.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.83.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.83.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.83.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.84.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.84.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.84.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.85.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.85.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.85.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.86.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.86.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.86.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.87.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.87.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.87.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.88.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.88.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.88.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.89.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.89.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.89.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.9.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.9.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.9.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.90.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.90.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.90.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.91.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.91.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.91.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.92.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.92.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.92.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.93.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.93.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.93.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.94.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.94.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.94.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.95.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.95.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.95.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.96.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.96.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.96.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.97.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.97.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.97.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.98.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.98.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.98.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.99.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.99.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.experts.99.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.gate.e_score_correction_bias": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.gate.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.shared_experts.down_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.shared_experts.gate_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.mlp.shared_experts.up_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.post_attention_layernorm.weight": "model-00088-of-00092.safetensors", + "model.layers.87.self_attn.k_norm.weight": "model-00088-of-00092.safetensors", + "model.layers.87.self_attn.k_proj.bias": "model-00088-of-00092.safetensors", + "model.layers.87.self_attn.k_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.self_attn.o_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.self_attn.q_norm.weight": "model-00088-of-00092.safetensors", + "model.layers.87.self_attn.q_proj.bias": "model-00088-of-00092.safetensors", + "model.layers.87.self_attn.q_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.87.self_attn.v_proj.bias": "model-00088-of-00092.safetensors", + "model.layers.87.self_attn.v_proj.weight": "model-00088-of-00092.safetensors", + "model.layers.88.input_layernorm.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.0.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.0.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.0.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.1.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.1.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.1.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.10.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.10.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.10.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.100.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.100.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.100.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.101.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.101.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.101.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.102.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.102.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.102.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.103.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.103.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.103.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.104.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.104.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.104.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.105.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.105.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.105.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.106.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.106.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.106.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.107.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.107.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.107.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.108.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.108.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.108.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.109.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.109.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.109.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.11.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.11.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.11.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.110.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.110.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.110.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.111.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.111.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.111.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.112.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.112.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.112.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.113.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.113.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.113.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.114.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.114.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.114.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.115.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.115.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.115.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.116.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.116.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.116.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.117.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.117.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.117.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.118.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.118.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.118.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.119.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.119.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.119.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.12.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.12.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.12.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.120.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.120.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.120.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.121.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.121.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.121.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.122.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.122.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.122.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.123.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.123.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.123.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.124.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.124.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.124.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.125.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.125.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.125.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.126.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.126.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.126.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.127.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.127.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.127.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.128.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.128.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.128.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.129.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.129.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.129.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.13.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.13.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.13.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.130.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.130.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.130.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.131.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.131.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.131.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.132.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.132.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.132.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.133.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.133.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.133.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.134.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.134.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.134.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.135.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.135.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.135.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.136.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.136.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.136.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.137.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.137.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.137.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.138.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.138.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.138.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.139.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.139.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.139.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.14.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.14.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.14.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.140.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.140.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.140.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.141.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.141.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.141.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.142.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.142.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.142.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.143.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.143.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.143.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.144.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.144.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.144.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.145.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.145.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.145.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.146.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.146.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.146.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.147.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.147.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.147.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.148.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.148.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.148.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.149.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.149.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.149.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.15.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.15.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.15.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.150.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.150.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.150.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.151.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.151.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.151.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.152.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.152.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.152.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.153.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.153.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.153.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.154.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.154.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.154.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.155.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.155.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.155.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.156.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.156.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.156.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.157.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.157.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.157.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.158.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.158.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.158.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.159.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.159.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.159.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.16.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.16.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.16.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.17.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.17.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.17.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.18.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.18.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.18.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.19.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.19.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.19.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.2.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.2.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.2.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.20.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.20.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.20.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.21.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.21.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.21.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.22.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.22.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.22.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.23.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.23.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.23.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.24.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.24.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.24.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.25.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.25.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.25.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.26.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.26.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.26.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.27.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.27.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.27.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.28.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.28.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.28.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.29.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.29.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.29.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.3.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.3.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.3.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.30.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.30.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.30.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.31.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.31.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.31.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.32.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.32.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.32.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.33.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.33.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.33.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.34.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.34.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.34.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.35.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.35.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.35.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.36.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.36.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.36.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.37.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.37.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.37.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.38.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.38.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.38.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.39.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.39.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.39.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.4.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.4.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.4.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.40.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.40.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.40.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.41.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.41.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.41.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.42.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.42.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.42.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.43.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.43.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.43.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.44.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.44.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.44.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.45.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.45.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.45.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.46.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.46.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.46.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.47.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.47.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.47.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.48.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.48.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.48.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.49.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.49.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.49.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.5.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.5.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.5.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.50.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.50.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.50.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.51.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.51.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.51.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.52.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.52.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.52.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.53.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.53.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.53.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.54.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.54.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.54.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.55.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.55.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.55.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.56.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.56.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.56.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.57.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.57.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.57.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.58.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.58.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.58.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.59.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.59.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.59.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.6.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.6.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.6.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.60.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.60.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.60.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.61.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.61.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.61.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.62.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.62.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.62.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.63.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.63.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.63.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.64.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.64.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.64.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.65.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.65.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.65.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.66.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.66.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.66.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.67.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.67.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.67.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.68.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.68.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.68.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.69.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.69.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.69.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.7.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.7.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.7.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.70.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.70.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.70.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.71.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.71.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.71.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.72.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.72.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.72.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.73.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.73.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.73.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.74.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.74.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.74.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.75.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.75.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.75.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.76.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.76.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.76.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.77.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.77.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.77.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.78.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.78.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.78.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.79.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.79.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.79.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.8.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.8.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.8.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.80.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.80.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.80.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.81.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.81.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.81.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.82.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.82.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.82.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.83.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.83.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.83.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.84.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.84.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.84.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.85.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.85.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.85.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.86.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.86.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.86.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.87.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.87.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.87.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.88.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.88.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.88.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.89.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.89.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.89.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.9.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.9.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.9.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.90.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.90.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.90.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.91.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.91.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.91.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.92.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.92.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.92.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.93.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.93.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.93.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.94.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.94.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.94.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.95.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.95.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.95.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.96.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.96.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.96.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.97.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.97.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.97.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.98.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.98.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.98.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.99.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.99.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.experts.99.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.gate.e_score_correction_bias": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.gate.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.shared_experts.down_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.shared_experts.gate_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.mlp.shared_experts.up_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.post_attention_layernorm.weight": "model-00089-of-00092.safetensors", + "model.layers.88.self_attn.k_norm.weight": "model-00089-of-00092.safetensors", + "model.layers.88.self_attn.k_proj.bias": "model-00089-of-00092.safetensors", + "model.layers.88.self_attn.k_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.self_attn.o_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.self_attn.q_norm.weight": "model-00089-of-00092.safetensors", + "model.layers.88.self_attn.q_proj.bias": "model-00089-of-00092.safetensors", + "model.layers.88.self_attn.q_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.88.self_attn.v_proj.bias": "model-00089-of-00092.safetensors", + "model.layers.88.self_attn.v_proj.weight": "model-00089-of-00092.safetensors", + "model.layers.89.input_layernorm.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.0.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.0.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.0.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.1.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.1.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.1.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.10.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.10.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.10.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.100.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.100.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.100.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.101.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.101.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.101.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.102.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.102.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.102.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.103.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.103.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.103.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.104.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.104.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.104.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.105.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.105.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.105.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.106.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.106.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.106.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.107.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.107.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.107.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.108.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.108.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.108.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.109.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.109.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.109.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.11.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.11.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.11.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.110.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.110.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.110.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.111.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.111.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.111.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.112.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.112.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.112.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.113.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.113.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.113.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.114.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.114.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.114.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.115.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.115.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.115.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.116.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.116.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.116.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.117.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.117.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.117.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.118.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.118.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.118.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.119.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.119.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.119.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.12.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.12.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.12.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.120.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.120.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.120.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.121.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.121.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.121.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.122.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.122.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.122.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.123.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.123.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.123.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.124.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.124.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.124.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.125.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.125.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.125.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.126.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.126.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.126.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.127.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.127.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.127.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.128.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.128.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.128.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.129.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.129.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.129.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.13.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.13.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.13.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.130.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.130.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.130.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.131.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.131.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.131.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.132.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.132.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.132.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.133.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.133.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.133.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.134.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.134.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.134.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.135.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.135.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.135.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.136.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.136.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.136.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.137.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.137.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.137.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.138.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.138.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.138.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.139.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.139.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.139.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.14.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.14.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.14.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.140.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.140.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.140.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.141.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.141.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.141.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.142.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.142.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.142.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.143.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.143.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.143.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.144.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.144.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.144.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.145.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.145.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.145.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.146.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.146.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.146.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.147.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.147.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.147.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.148.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.148.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.148.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.149.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.149.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.149.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.15.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.15.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.15.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.150.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.150.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.150.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.151.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.151.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.151.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.152.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.152.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.152.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.153.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.153.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.153.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.154.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.154.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.154.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.155.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.155.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.155.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.156.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.156.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.156.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.157.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.157.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.157.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.158.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.158.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.158.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.159.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.159.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.159.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.16.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.16.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.16.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.17.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.17.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.17.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.18.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.18.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.18.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.19.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.19.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.19.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.2.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.2.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.2.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.20.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.20.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.20.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.21.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.21.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.21.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.22.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.22.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.22.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.23.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.23.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.23.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.24.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.24.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.24.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.25.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.25.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.25.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.26.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.26.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.26.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.27.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.27.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.27.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.28.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.28.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.28.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.29.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.29.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.29.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.3.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.3.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.3.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.30.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.30.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.30.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.31.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.31.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.31.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.32.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.32.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.32.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.33.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.33.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.33.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.34.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.34.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.34.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.35.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.35.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.35.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.36.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.36.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.36.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.37.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.37.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.37.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.38.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.38.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.38.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.39.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.39.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.39.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.4.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.4.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.4.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.40.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.40.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.40.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.41.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.41.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.41.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.42.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.42.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.42.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.43.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.43.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.43.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.44.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.44.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.44.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.45.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.45.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.45.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.46.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.46.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.46.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.47.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.47.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.47.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.48.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.48.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.48.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.49.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.49.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.49.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.5.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.5.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.5.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.50.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.50.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.50.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.51.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.51.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.51.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.52.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.52.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.52.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.53.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.53.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.53.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.54.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.54.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.54.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.55.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.55.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.55.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.56.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.56.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.56.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.57.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.57.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.57.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.58.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.58.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.58.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.59.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.59.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.59.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.6.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.6.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.6.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.60.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.60.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.60.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.61.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.61.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.61.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.62.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.62.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.62.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.63.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.63.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.63.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.64.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.64.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.64.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.65.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.65.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.65.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.66.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.66.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.66.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.67.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.67.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.67.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.68.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.68.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.68.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.69.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.69.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.69.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.7.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.7.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.7.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.70.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.70.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.70.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.71.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.71.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.71.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.72.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.72.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.72.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.73.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.73.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.73.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.74.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.74.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.74.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.75.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.75.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.75.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.76.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.76.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.76.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.77.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.77.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.77.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.78.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.78.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.78.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.79.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.79.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.79.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.8.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.8.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.8.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.80.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.80.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.80.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.81.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.81.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.81.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.82.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.82.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.82.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.83.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.83.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.83.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.84.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.84.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.84.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.85.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.85.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.85.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.86.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.86.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.86.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.87.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.87.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.87.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.88.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.88.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.88.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.89.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.89.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.89.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.9.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.9.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.9.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.90.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.90.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.90.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.91.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.91.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.91.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.92.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.92.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.92.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.93.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.93.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.93.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.94.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.94.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.94.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.95.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.95.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.95.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.96.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.96.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.96.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.97.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.97.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.97.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.98.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.98.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.98.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.99.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.99.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.experts.99.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.gate.e_score_correction_bias": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.gate.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.shared_experts.down_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.shared_experts.gate_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.mlp.shared_experts.up_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.post_attention_layernorm.weight": "model-00090-of-00092.safetensors", + "model.layers.89.self_attn.k_norm.weight": "model-00090-of-00092.safetensors", + "model.layers.89.self_attn.k_proj.bias": "model-00090-of-00092.safetensors", + "model.layers.89.self_attn.k_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.self_attn.o_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.self_attn.q_norm.weight": "model-00090-of-00092.safetensors", + "model.layers.89.self_attn.q_proj.bias": "model-00090-of-00092.safetensors", + "model.layers.89.self_attn.q_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.89.self_attn.v_proj.bias": "model-00090-of-00092.safetensors", + "model.layers.89.self_attn.v_proj.weight": "model-00090-of-00092.safetensors", + "model.layers.90.input_layernorm.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.0.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.0.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.0.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.1.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.1.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.1.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.10.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.10.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.10.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.100.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.100.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.100.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.101.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.101.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.101.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.102.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.102.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.102.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.103.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.103.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.103.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.104.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.104.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.104.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.105.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.105.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.105.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.106.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.106.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.106.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.107.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.107.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.107.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.108.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.108.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.108.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.109.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.109.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.109.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.11.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.11.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.11.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.110.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.110.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.110.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.111.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.111.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.111.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.112.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.112.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.112.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.113.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.113.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.113.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.114.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.114.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.114.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.115.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.115.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.115.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.116.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.116.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.116.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.117.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.117.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.117.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.118.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.118.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.118.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.119.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.119.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.119.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.12.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.12.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.12.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.120.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.120.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.120.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.121.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.121.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.121.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.122.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.122.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.122.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.123.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.123.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.123.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.124.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.124.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.124.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.125.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.125.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.125.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.126.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.126.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.126.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.127.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.127.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.127.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.128.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.128.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.128.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.129.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.129.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.129.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.13.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.13.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.13.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.130.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.130.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.130.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.131.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.131.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.131.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.132.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.132.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.132.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.133.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.133.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.133.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.134.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.134.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.134.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.135.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.135.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.135.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.136.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.136.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.136.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.137.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.137.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.137.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.138.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.138.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.138.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.139.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.139.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.139.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.14.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.14.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.14.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.140.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.140.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.140.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.141.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.141.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.141.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.142.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.142.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.142.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.143.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.143.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.143.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.144.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.144.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.144.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.145.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.145.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.145.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.146.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.146.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.146.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.147.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.147.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.147.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.148.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.148.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.148.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.149.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.149.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.149.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.15.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.15.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.15.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.150.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.150.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.150.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.151.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.151.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.151.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.152.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.152.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.152.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.153.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.153.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.153.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.154.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.154.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.154.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.155.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.155.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.155.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.156.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.156.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.156.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.157.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.157.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.157.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.158.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.158.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.158.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.159.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.159.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.159.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.16.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.16.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.16.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.17.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.17.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.17.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.18.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.18.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.18.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.19.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.19.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.19.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.2.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.2.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.2.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.20.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.20.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.20.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.21.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.21.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.21.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.22.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.22.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.22.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.23.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.23.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.23.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.24.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.24.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.24.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.25.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.25.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.25.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.26.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.26.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.26.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.27.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.27.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.27.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.28.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.28.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.28.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.29.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.29.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.29.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.3.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.3.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.3.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.30.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.30.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.30.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.31.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.31.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.31.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.32.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.32.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.32.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.33.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.33.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.33.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.34.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.34.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.34.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.35.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.35.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.35.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.36.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.36.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.36.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.37.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.37.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.37.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.38.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.38.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.38.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.39.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.39.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.39.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.4.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.4.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.4.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.40.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.40.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.40.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.41.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.41.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.41.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.42.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.42.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.42.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.43.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.43.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.43.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.44.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.44.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.44.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.45.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.45.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.45.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.46.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.46.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.46.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.47.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.47.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.47.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.48.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.48.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.48.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.49.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.49.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.49.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.5.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.5.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.5.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.50.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.50.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.50.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.51.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.51.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.51.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.52.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.52.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.52.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.53.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.53.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.53.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.54.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.54.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.54.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.55.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.55.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.55.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.56.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.56.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.56.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.57.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.57.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.57.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.58.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.58.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.58.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.59.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.59.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.59.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.6.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.6.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.6.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.60.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.60.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.60.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.61.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.61.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.61.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.62.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.62.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.62.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.63.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.63.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.63.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.64.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.64.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.64.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.65.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.65.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.65.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.66.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.66.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.66.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.67.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.67.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.67.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.68.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.68.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.68.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.69.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.69.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.69.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.7.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.7.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.7.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.70.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.70.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.70.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.71.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.71.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.71.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.72.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.72.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.72.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.73.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.73.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.73.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.74.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.74.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.74.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.75.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.75.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.75.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.76.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.76.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.76.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.77.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.77.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.77.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.78.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.78.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.78.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.79.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.79.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.79.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.8.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.8.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.8.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.80.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.80.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.80.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.81.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.81.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.81.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.82.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.82.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.82.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.83.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.83.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.83.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.84.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.84.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.84.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.85.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.85.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.85.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.86.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.86.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.86.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.87.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.87.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.87.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.88.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.88.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.88.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.89.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.89.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.89.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.9.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.9.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.9.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.90.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.90.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.90.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.91.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.91.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.91.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.92.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.92.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.92.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.93.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.93.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.93.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.94.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.94.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.94.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.95.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.95.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.95.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.96.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.96.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.96.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.97.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.97.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.97.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.98.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.98.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.98.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.99.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.99.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.experts.99.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.gate.e_score_correction_bias": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.gate.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.shared_experts.down_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.shared_experts.gate_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.mlp.shared_experts.up_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.post_attention_layernorm.weight": "model-00091-of-00092.safetensors", + "model.layers.90.self_attn.k_norm.weight": "model-00091-of-00092.safetensors", + "model.layers.90.self_attn.k_proj.bias": "model-00091-of-00092.safetensors", + "model.layers.90.self_attn.k_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.self_attn.o_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.self_attn.q_norm.weight": "model-00091-of-00092.safetensors", + "model.layers.90.self_attn.q_proj.bias": "model-00091-of-00092.safetensors", + "model.layers.90.self_attn.q_proj.weight": "model-00091-of-00092.safetensors", + "model.layers.90.self_attn.v_proj.bias": "model-00091-of-00092.safetensors", + "model.layers.90.self_attn.v_proj.weight": "model-00091-of-00092.safetensors", + "lm_head.weight": "model-00092-of-00092.safetensors", + "model.layers.91.input_layernorm.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.0.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.0.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.0.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.1.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.1.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.1.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.10.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.10.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.10.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.100.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.100.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.100.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.101.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.101.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.101.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.102.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.102.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.102.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.103.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.103.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.103.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.104.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.104.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.104.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.105.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.105.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.105.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.106.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.106.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.106.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.107.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.107.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.107.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.108.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.108.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.108.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.109.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.109.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.109.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.11.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.11.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.11.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.110.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.110.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.110.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.111.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.111.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.111.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.112.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.112.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.112.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.113.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.113.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.113.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.114.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.114.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.114.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.115.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.115.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.115.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.116.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.116.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.116.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.117.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.117.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.117.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.118.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.118.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.118.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.119.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.119.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.119.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.12.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.12.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.12.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.120.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.120.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.120.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.121.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.121.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.121.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.122.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.122.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.122.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.123.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.123.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.123.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.124.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.124.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.124.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.125.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.125.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.125.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.126.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.126.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.126.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.127.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.127.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.127.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.128.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.128.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.128.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.129.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.129.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.129.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.13.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.13.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.13.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.130.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.130.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.130.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.131.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.131.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.131.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.132.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.132.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.132.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.133.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.133.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.133.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.134.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.134.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.134.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.135.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.135.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.135.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.136.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.136.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.136.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.137.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.137.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.137.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.138.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.138.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.138.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.139.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.139.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.139.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.14.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.14.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.14.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.140.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.140.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.140.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.141.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.141.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.141.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.142.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.142.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.142.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.143.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.143.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.143.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.144.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.144.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.144.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.145.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.145.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.145.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.146.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.146.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.146.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.147.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.147.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.147.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.148.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.148.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.148.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.149.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.149.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.149.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.15.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.15.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.15.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.150.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.150.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.150.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.151.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.151.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.151.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.152.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.152.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.152.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.153.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.153.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.153.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.154.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.154.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.154.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.155.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.155.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.155.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.156.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.156.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.156.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.157.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.157.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.157.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.158.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.158.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.158.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.159.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.159.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.159.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.16.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.16.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.16.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.17.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.17.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.17.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.18.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.18.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.18.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.19.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.19.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.19.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.2.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.2.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.2.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.20.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.20.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.20.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.21.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.21.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.21.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.22.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.22.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.22.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.23.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.23.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.23.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.24.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.24.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.24.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.25.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.25.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.25.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.26.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.26.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.26.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.27.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.27.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.27.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.28.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.28.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.28.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.29.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.29.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.29.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.3.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.3.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.3.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.30.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.30.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.30.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.31.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.31.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.31.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.32.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.32.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.32.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.33.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.33.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.33.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.34.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.34.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.34.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.35.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.35.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.35.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.36.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.36.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.36.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.37.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.37.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.37.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.38.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.38.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.38.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.39.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.39.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.39.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.4.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.4.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.4.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.40.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.40.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.40.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.41.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.41.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.41.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.42.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.42.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.42.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.43.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.43.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.43.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.44.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.44.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.44.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.45.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.45.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.45.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.46.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.46.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.46.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.47.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.47.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.47.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.48.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.48.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.48.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.49.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.49.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.49.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.5.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.5.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.5.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.50.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.50.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.50.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.51.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.51.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.51.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.52.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.52.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.52.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.53.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.53.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.53.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.54.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.54.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.54.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.55.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.55.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.55.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.56.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.56.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.56.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.57.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.57.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.57.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.58.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.58.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.58.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.59.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.59.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.59.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.6.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.6.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.6.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.60.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.60.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.60.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.61.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.61.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.61.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.62.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.62.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.62.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.63.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.63.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.63.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.64.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.64.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.64.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.65.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.65.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.65.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.66.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.66.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.66.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.67.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.67.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.67.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.68.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.68.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.68.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.69.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.69.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.69.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.7.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.7.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.7.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.70.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.70.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.70.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.71.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.71.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.71.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.72.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.72.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.72.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.73.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.73.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.73.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.74.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.74.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.74.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.75.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.75.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.75.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.76.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.76.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.76.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.77.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.77.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.77.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.78.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.78.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.78.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.79.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.79.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.79.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.8.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.8.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.8.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.80.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.80.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.80.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.81.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.81.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.81.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.82.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.82.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.82.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.83.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.83.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.83.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.84.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.84.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.84.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.85.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.85.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.85.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.86.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.86.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.86.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.87.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.87.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.87.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.88.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.88.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.88.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.89.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.89.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.89.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.9.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.9.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.9.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.90.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.90.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.90.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.91.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.91.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.91.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.92.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.92.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.92.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.93.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.93.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.93.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.94.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.94.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.94.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.95.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.95.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.95.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.96.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.96.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.96.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.97.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.97.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.97.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.98.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.98.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.98.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.99.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.99.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.experts.99.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.gate.e_score_correction_bias": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.gate.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.shared_experts.down_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.shared_experts.gate_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.mlp.shared_experts.up_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.post_attention_layernorm.weight": "model-00092-of-00092.safetensors", + "model.layers.91.self_attn.k_norm.weight": "model-00092-of-00092.safetensors", + "model.layers.91.self_attn.k_proj.bias": "model-00092-of-00092.safetensors", + "model.layers.91.self_attn.k_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.self_attn.o_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.self_attn.q_norm.weight": "model-00092-of-00092.safetensors", + "model.layers.91.self_attn.q_proj.bias": "model-00092-of-00092.safetensors", + "model.layers.91.self_attn.q_proj.weight": "model-00092-of-00092.safetensors", + "model.layers.91.self_attn.v_proj.bias": "model-00092-of-00092.safetensors", + "model.layers.91.self_attn.v_proj.weight": "model-00092-of-00092.safetensors", + "model.norm.weight": "model-00092-of-00092.safetensors", + "model.layers.92.eh_proj.weight": "mtp.safetensors", + "model.layers.92.enorm.weight": "mtp.safetensors", + "model.layers.92.hnorm.weight": "mtp.safetensors", + "model.layers.92.input_layernorm.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.0.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.0.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.0.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.1.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.1.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.1.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.10.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.10.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.10.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.100.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.100.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.100.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.101.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.101.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.101.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.102.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.102.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.102.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.103.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.103.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.103.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.104.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.104.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.104.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.105.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.105.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.105.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.106.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.106.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.106.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.107.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.107.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.107.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.108.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.108.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.108.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.109.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.109.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.109.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.11.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.11.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.11.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.110.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.110.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.110.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.111.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.111.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.111.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.112.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.112.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.112.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.113.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.113.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.113.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.114.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.114.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.114.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.115.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.115.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.115.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.116.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.116.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.116.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.117.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.117.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.117.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.118.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.118.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.118.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.119.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.119.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.119.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.12.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.12.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.12.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.120.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.120.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.120.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.121.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.121.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.121.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.122.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.122.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.122.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.123.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.123.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.123.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.124.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.124.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.124.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.125.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.125.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.125.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.126.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.126.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.126.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.127.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.127.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.127.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.128.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.128.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.128.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.129.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.129.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.129.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.13.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.13.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.13.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.130.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.130.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.130.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.131.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.131.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.131.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.132.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.132.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.132.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.133.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.133.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.133.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.134.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.134.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.134.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.135.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.135.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.135.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.136.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.136.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.136.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.137.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.137.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.137.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.138.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.138.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.138.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.139.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.139.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.139.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.14.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.14.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.14.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.140.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.140.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.140.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.141.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.141.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.141.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.142.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.142.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.142.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.143.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.143.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.143.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.144.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.144.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.144.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.145.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.145.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.145.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.146.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.146.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.146.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.147.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.147.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.147.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.148.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.148.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.148.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.149.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.149.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.149.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.15.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.15.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.15.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.150.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.150.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.150.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.151.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.151.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.151.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.152.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.152.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.152.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.153.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.153.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.153.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.154.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.154.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.154.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.155.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.155.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.155.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.156.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.156.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.156.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.157.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.157.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.157.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.158.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.158.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.158.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.159.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.159.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.159.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.16.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.16.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.16.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.17.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.17.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.17.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.18.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.18.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.18.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.19.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.19.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.19.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.2.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.2.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.2.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.20.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.20.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.20.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.21.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.21.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.21.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.22.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.22.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.22.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.23.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.23.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.23.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.24.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.24.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.24.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.25.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.25.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.25.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.26.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.26.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.26.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.27.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.27.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.27.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.28.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.28.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.28.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.29.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.29.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.29.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.3.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.3.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.3.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.30.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.30.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.30.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.31.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.31.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.31.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.32.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.32.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.32.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.33.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.33.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.33.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.34.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.34.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.34.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.35.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.35.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.35.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.36.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.36.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.36.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.37.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.37.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.37.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.38.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.38.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.38.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.39.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.39.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.39.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.4.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.4.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.4.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.40.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.40.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.40.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.41.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.41.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.41.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.42.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.42.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.42.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.43.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.43.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.43.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.44.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.44.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.44.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.45.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.45.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.45.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.46.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.46.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.46.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.47.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.47.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.47.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.48.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.48.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.48.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.49.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.49.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.49.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.5.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.5.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.5.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.50.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.50.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.50.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.51.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.51.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.51.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.52.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.52.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.52.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.53.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.53.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.53.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.54.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.54.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.54.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.55.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.55.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.55.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.56.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.56.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.56.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.57.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.57.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.57.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.58.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.58.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.58.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.59.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.59.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.59.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.6.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.6.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.6.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.60.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.60.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.60.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.61.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.61.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.61.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.62.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.62.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.62.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.63.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.63.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.63.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.64.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.64.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.64.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.65.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.65.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.65.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.66.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.66.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.66.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.67.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.67.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.67.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.68.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.68.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.68.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.69.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.69.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.69.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.7.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.7.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.7.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.70.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.70.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.70.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.71.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.71.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.71.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.72.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.72.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.72.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.73.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.73.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.73.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.74.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.74.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.74.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.75.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.75.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.75.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.76.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.76.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.76.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.77.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.77.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.77.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.78.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.78.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.78.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.79.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.79.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.79.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.8.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.8.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.8.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.80.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.80.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.80.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.81.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.81.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.81.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.82.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.82.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.82.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.83.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.83.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.83.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.84.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.84.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.84.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.85.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.85.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.85.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.86.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.86.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.86.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.87.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.87.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.87.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.88.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.88.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.88.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.89.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.89.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.89.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.9.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.9.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.9.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.90.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.90.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.90.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.91.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.91.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.91.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.92.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.92.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.92.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.93.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.93.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.93.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.94.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.94.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.94.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.95.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.95.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.95.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.96.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.96.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.96.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.97.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.97.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.97.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.98.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.98.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.98.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.99.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.99.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.experts.99.up_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.gate.e_score_correction_bias": "mtp.safetensors", + "model.layers.92.mlp.gate.weight": "mtp.safetensors", + "model.layers.92.mlp.shared_experts.down_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.shared_experts.gate_proj.weight": "mtp.safetensors", + "model.layers.92.mlp.shared_experts.up_proj.weight": "mtp.safetensors", + "model.layers.92.post_attention_layernorm.weight": "mtp.safetensors", + "model.layers.92.self_attn.k_norm.weight": "mtp.safetensors", + "model.layers.92.self_attn.k_proj.bias": "mtp.safetensors", + "model.layers.92.self_attn.k_proj.weight": "mtp.safetensors", + "model.layers.92.self_attn.o_proj.weight": "mtp.safetensors", + "model.layers.92.self_attn.q_norm.weight": "mtp.safetensors", + "model.layers.92.self_attn.q_proj.bias": "mtp.safetensors", + "model.layers.92.self_attn.q_proj.weight": "mtp.safetensors", + "model.layers.92.self_attn.v_proj.bias": "mtp.safetensors", + "model.layers.92.self_attn.v_proj.weight": "mtp.safetensors", + "model.layers.92.shared_head.norm.weight": "mtp.safetensors" + } +} \ No newline at end of file diff --git a/mtp.safetensors b/mtp.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f5176f4a41901192f4a04fc830af6a21108903ff --- /dev/null +++ b/mtp.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74a26e5f1245a153f3a9ab94219266aeb632e9dd90ce63fbada1a8c39f47924b +size 7976202392 diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..43a71efad1ab3f7e4d66d1e48e7cc44f68f21f3a --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9340665016419c825c4bdabbcc9acc43b7ca2c68ce142724afa829abb1be5efd +size 19970699 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..053f12c9b03d5acbcc921042ea0c87a6baa5d3f7 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,325 @@ +{ + "added_tokens_decoder": { + "151329": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151330": { + "content": "[MASK]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151331": { + "content": "[gMASK]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151332": { + "content": "[sMASK]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151333": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151334": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151335": { + "content": "<|system|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151336": { + "content": "<|user|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151337": { + "content": "<|assistant|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151338": { + "content": "<|observation|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151339": { + "content": "<|begin_of_image|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151340": { + "content": "<|end_of_image|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151341": { + "content": "<|begin_of_video|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151342": { + "content": "<|end_of_video|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151343": { + "content": "<|begin_of_audio|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151344": { + "content": "<|end_of_audio|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151345": { + "content": "<|begin_of_transcription|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151346": { + "content": "<|end_of_transcription|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151347": { + "content": "<|code_prefix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151348": { + "content": "<|code_middle|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151349": { + "content": "<|code_suffix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151350": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151351": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151352": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151353": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151354": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151355": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151356": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151357": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151358": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151359": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151360": { + "content": "/nothink", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151361": { + "content": "<|begin_of_box|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151362": { + "content": "<|end_of_box|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151363": { + "content": "<|image|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151364": { + "content": "<|video|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + } + }, + "additional_special_tokens": [ + "<|endoftext|>", + "[MASK]", + "[gMASK]", + "[sMASK]", + "", + "", + "<|system|>", + "<|user|>", + "<|assistant|>", + "<|observation|>", + "<|begin_of_image|>", + "<|end_of_image|>", + "<|begin_of_video|>", + "<|end_of_video|>", + "<|begin_of_audio|>", + "<|end_of_audio|>", + "<|begin_of_transcription|>", + "<|end_of_transcription|>", + "<|code_prefix|>", + "<|code_middle|>", + "<|code_suffix|>", + "/nothink" + ], + "clean_up_tokenization_spaces": false, + "do_lower_case": false, + "eos_token": "<|endoftext|>", + "extra_special_tokens": {}, + "model_max_length": 128000, + "pad_token": "<|endoftext|>", + "padding_side": "left", + "remove_space": false, + "tokenizer_class": "PreTrainedTokenizer" +}