Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* 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

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

config.json

@@ -0,0 +1,140 @@
+{
+  "architectures": [
+    "Qwen2MoeForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "decoder_sparse_step": 1,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 5632,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 21,
+  "mlp_only_layers": [],
+  "model_type": "qwen2_moe",
+  "moe_intermediate_size": 1408,
+  "norm_topk_prob": false,
+  "num_attention_heads": 16,
+  "num_experts": 60,
+  "num_experts_per_tok": 4,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 16,
+  "output_router_logits": false,
+  "qkv_bias": true,
+  "quantization_config": {
+    "algo_config": [],
+    "exclude": [
+      "model.layers.0.mlp.gate",
+      "model.layers.0.mlp.shared_expert_gate",
+      "model.layers.1.mlp.gate",
+      "model.layers.1.mlp.shared_expert_gate",
+      "model.layers.2.mlp.gate",
+      "model.layers.2.mlp.shared_expert_gate",
+      "model.layers.3.mlp.gate",
+      "model.layers.3.mlp.shared_expert_gate",
+      "model.layers.4.mlp.gate",
+      "model.layers.4.mlp.shared_expert_gate",
+      "model.layers.5.mlp.gate",
+      "model.layers.5.mlp.shared_expert_gate",
+      "model.layers.6.mlp.gate",
+      "model.layers.6.mlp.shared_expert_gate",
+      "model.layers.7.mlp.gate",
+      "model.layers.7.mlp.shared_expert_gate",
+      "model.layers.8.mlp.gate",
+      "model.layers.8.mlp.shared_expert_gate",
+      "model.layers.9.mlp.gate",
+      "model.layers.9.mlp.shared_expert_gate",
+      "model.layers.10.mlp.gate",
+      "model.layers.10.mlp.shared_expert_gate",
+      "model.layers.11.mlp.gate",
+      "model.layers.11.mlp.shared_expert_gate",
+      "model.layers.12.mlp.gate",
+      "model.layers.12.mlp.shared_expert_gate",
+      "model.layers.13.mlp.gate",
+      "model.layers.13.mlp.shared_expert_gate",
+      "model.layers.14.mlp.gate",
+      "model.layers.14.mlp.shared_expert_gate",
+      "model.layers.15.mlp.gate",
+      "model.layers.15.mlp.shared_expert_gate",
+      "model.layers.16.mlp.gate",
+      "model.layers.16.mlp.shared_expert_gate",
+      "model.layers.17.mlp.gate",
+      "model.layers.17.mlp.shared_expert_gate",
+      "model.layers.18.mlp.gate",
+      "model.layers.18.mlp.shared_expert_gate",
+      "model.layers.19.mlp.gate",
+      "model.layers.19.mlp.shared_expert_gate",
+      "model.layers.20.mlp.gate",
+      "model.layers.20.mlp.shared_expert_gate",
+      "model.layers.21.mlp.gate",
+      "model.layers.21.mlp.shared_expert_gate",
+      "model.layers.22.mlp.gate",
+      "model.layers.22.mlp.shared_expert_gate",
+      "model.layers.23.mlp.gate",
+      "model.layers.23.mlp.shared_expert_gate",
+      "lm_head"
+    ],
+    "export": {
+      "kv_cache_group": [],
+      "min_kv_scale": 0.0,
+      "pack_method": "reorder",
+      "weight_format": "real_quantized",
+      "weight_merge_groups": null
+    },
+    "global_quant_config": {
+      "bias": null,
+      "input_tensors": {
+        "ch_axis": -1,
+        "dtype": "fp6_e2m3",
+        "group_size": 32,
+        "is_dynamic": true,
+        "is_scale_quant": false,
+        "mx_element_dtype": null,
+        "observer_cls": "PerBlockMXObserver",
+        "qscheme": "per_group",
+        "round_method": "half_even",
+        "scale_calculation_mode": "even",
+        "scale_format": "e8m0",
+        "scale_type": "float",
+        "symmetric": null
+      },
+      "output_tensors": null,
+      "target_device": null,
+      "weight": {
+        "ch_axis": -1,
+        "dtype": "fp4",
+        "group_size": 32,
+        "is_dynamic": false,
+        "is_scale_quant": false,
+        "mx_element_dtype": null,
+        "observer_cls": "PerBlockMXObserver",
+        "qscheme": "per_group",
+        "round_method": "half_even",
+        "scale_calculation_mode": "even",
+        "scale_format": "e8m0",
+        "scale_type": "float",
+        "symmetric": null
+      }
+    },
+    "layer_quant_config": {},
+    "layer_type_quant_config": {},
+    "quant_method": "quark",
+    "quant_mode": "eager_mode",
+    "softmax_quant_spec": null,
+    "version": "0.10+a98b801d2b"
+  },
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "router_aux_loss_coef": 0.001,
+  "shared_expert_intermediate_size": 5632,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.3",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.51.3"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a6e64f06a6a0270596cfbdd648ee10599c9e17fd1134ae79b858e82bb2e91ad
+size 4999525848

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:864574bcc5405152fa0940d61715764299e81e479a8cf8f3c96c32f160614300
+size 3525683736

special_tokens_map.json

@@ -0,0 +1,14 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|im_end|>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28a3805f96182b66cdf5db141c4c6e01f8c184651137ae6080ff7877db568a92
+size 11418528

tokenizer_config.json

@@ -0,0 +1,45 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 32768,
+  "pad_token": "<|im_end|>",
+  "padding_side": "left",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}