Commit
·
728cd7b
1
Parent(s):
92c7415
Upload LlamaForCausalLM
Browse files- config.json +26 -0
- generation_config.json +9 -0
- pytorch_model-00001-of-00023.bin +3 -0
- pytorch_model-00002-of-00023.bin +3 -0
- pytorch_model-00003-of-00023.bin +3 -0
- pytorch_model-00004-of-00023.bin +3 -0
- pytorch_model-00005-of-00023.bin +3 -0
- pytorch_model-00006-of-00023.bin +3 -0
- pytorch_model-00007-of-00023.bin +3 -0
- pytorch_model-00008-of-00023.bin +3 -0
- pytorch_model-00009-of-00023.bin +3 -0
- pytorch_model-00010-of-00023.bin +3 -0
- pytorch_model-00011-of-00023.bin +3 -0
- pytorch_model-00012-of-00023.bin +3 -0
- pytorch_model-00013-of-00023.bin +3 -0
- pytorch_model-00014-of-00023.bin +3 -0
- pytorch_model-00015-of-00023.bin +3 -0
- pytorch_model-00016-of-00023.bin +3 -0
- pytorch_model-00017-of-00023.bin +3 -0
- pytorch_model-00018-of-00023.bin +3 -0
- pytorch_model-00019-of-00023.bin +3 -0
- pytorch_model-00020-of-00023.bin +3 -0
- pytorch_model-00021-of-00023.bin +3 -0
- pytorch_model-00022-of-00023.bin +3 -0
- pytorch_model-00023-of-00023.bin +3 -0
- pytorch_model.bin.index.json +298 -0
config.json
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "meta-llama/Llama-2-7b-hf",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"LlamaForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"bos_token_id": 1,
|
| 7 |
+
"eos_token_id": 2,
|
| 8 |
+
"hidden_act": "silu",
|
| 9 |
+
"hidden_size": 4096,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"intermediate_size": 11008,
|
| 12 |
+
"max_position_embeddings": 4096,
|
| 13 |
+
"model_type": "llama",
|
| 14 |
+
"num_attention_heads": 32,
|
| 15 |
+
"num_hidden_layers": 32,
|
| 16 |
+
"num_key_value_heads": 32,
|
| 17 |
+
"pad_token_id": 0,
|
| 18 |
+
"pretraining_tp": 1,
|
| 19 |
+
"rms_norm_eps": 1e-05,
|
| 20 |
+
"rope_scaling": null,
|
| 21 |
+
"tie_word_embeddings": false,
|
| 22 |
+
"torch_dtype": "bfloat16",
|
| 23 |
+
"transformers_version": "4.32.0.dev0",
|
| 24 |
+
"use_cache": true,
|
| 25 |
+
"vocab_size": 32000
|
| 26 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 1,
|
| 3 |
+
"eos_token_id": 2,
|
| 4 |
+
"max_length": 4096,
|
| 5 |
+
"pad_token_id": 0,
|
| 6 |
+
"temperature": 0.9,
|
| 7 |
+
"top_p": 0.6,
|
| 8 |
+
"transformers_version": "4.32.0.dev0"
|
| 9 |
+
}
|
pytorch_model-00001-of-00023.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b49c532fd0094dc81c6d20b6f68a84ce32cad61b8b45806a6b2520dc985219af
|
| 3 |
+
size 576719696
|
pytorch_model-00002-of-00023.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7f3241494f93d08bc5ecb8eddf84fb82dca6d911b4f1a494dcf60034e05ce7b7
|
| 3 |
+
size 629184175
|
pytorch_model-00003-of-00023.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:47e8066e392daf52b8a063e37967fbc42548b2bae477877f09bb6766b5fe5533
|
| 3 |
+
size 585125973
|
pytorch_model-00004-of-00023.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b8f79e1456fddf8739e84f68593baee23b4dea2390d138df2ce61106aa8a6281
|
| 3 |
+
size 629184175
|
pytorch_model-00005-of-00023.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f96e872afc93bc4448307e9a559f240321c1e9a9be08c3a3c4ff3ce3777ec8ef
|
| 3 |
+
size 585125973
|
pytorch_model-00006-of-00023.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:91610e51ed292008c1052497f41803cdf9be8ba22ad090bb69ad36f05a5c1a24
|
| 3 |
+
size 629184175
|
pytorch_model-00007-of-00023.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ee09b658431180b180d19a6d0d58c2f989c6788559b44a18bb3e633e28ae6148
|
| 3 |
+
size 585125973
|
pytorch_model-00008-of-00023.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:897c5507954d539c58e7523b6fb16ec97600c1ea3fae2669ef519ace67658381
|
| 3 |
+
size 629184175
|
pytorch_model-00009-of-00023.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dfd2c481c2960d8fa357376f6f84c250c5312cbcae8a4d33611af3aa1bf764c4
|
| 3 |
+
size 585125973
|
pytorch_model-00010-of-00023.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fb088a9c7046ab691014e99cc054992881591035c346ab8d72893faeb1074664
|
| 3 |
+
size 629184175
|
pytorch_model-00011-of-00023.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:adf181a85f95ee9eb55e28d200ae245e2057cee949c1f8883402e48f3d0f023d
|
| 3 |
+
size 585125973
|
pytorch_model-00012-of-00023.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9f7769864785c4867008495107f4d7356662bdd57ae6b20bc1d2ed41c71f2df6
|
| 3 |
+
size 629184175
|
pytorch_model-00013-of-00023.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:581c412824a6dd066ef0edd4fa96812d1e86a26bcf6584c180338e58e6a58230
|
| 3 |
+
size 585125973
|
pytorch_model-00014-of-00023.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f94f4320a35fbf5b59840493b352a99968fef0ccfa477c039bf8d8d03f749c9a
|
| 3 |
+
size 629184175
|
pytorch_model-00015-of-00023.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3c67163edc2d1d4b1d0630f3e38411b43c9a73e06b0d0c2dd7367cf249048422
|
| 3 |
+
size 585125973
|
pytorch_model-00016-of-00023.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c73ed7f5455b565f5859881136158718105f97baa2f31775acd682852bb2517c
|
| 3 |
+
size 629184175
|
pytorch_model-00017-of-00023.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:219a25c8789046ce554ef90c5fef6b2ca9505521448585a56b5394aebc0c5e05
|
| 3 |
+
size 585125973
|
pytorch_model-00018-of-00023.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:46aec9e794a9c5048a63c487c385c35cc83e72953555e737a0fee79fca77cbf4
|
| 3 |
+
size 629184175
|
pytorch_model-00019-of-00023.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e9226713f3d8f6de6dbe0a300832cd8e1c3f534f9e25aea1ede83a1b1866eb41
|
| 3 |
+
size 585125973
|
pytorch_model-00020-of-00023.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:90a4cd04d4821e25ef74561e3bba82737b73392e7da43321f30e45cb0478110a
|
| 3 |
+
size 629184175
|
pytorch_model-00021-of-00023.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0e05fdffef18fe5bd7d1598e932c1734adef7f2a297beca5faed1a745b4a1418
|
| 3 |
+
size 585125973
|
pytorch_model-00022-of-00023.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c373981f14a6b524fd72b78c58e5f51994eaf8b4830ec5a3037be5860dd88af7
|
| 3 |
+
size 494973625
|
pytorch_model-00023-of-00023.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7d46405a9143a3cf35883f09f6ad5c71878ded91bd9f2d7277ef33083f659581
|
| 3 |
+
size 262144938
|
pytorch_model.bin.index.json
ADDED
|
@@ -0,0 +1,298 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 13476831232
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"lm_head.weight": "pytorch_model-00023-of-00023.bin",
|
| 7 |
+
"model.embed_tokens.weight": "pytorch_model-00001-of-00023.bin",
|
| 8 |
+
"model.layers.0.input_layernorm.weight": "pytorch_model-00002-of-00023.bin",
|
| 9 |
+
"model.layers.0.mlp.down_proj.weight": "pytorch_model-00002-of-00023.bin",
|
| 10 |
+
"model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00023.bin",
|
| 11 |
+
"model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00023.bin",
|
| 12 |
+
"model.layers.0.post_attention_layernorm.weight": "pytorch_model-00002-of-00023.bin",
|
| 13 |
+
"model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00023.bin",
|
| 14 |
+
"model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00023.bin",
|
| 15 |
+
"model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00023.bin",
|
| 16 |
+
"model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00023.bin",
|
| 17 |
+
"model.layers.1.input_layernorm.weight": "pytorch_model-00002-of-00023.bin",
|
| 18 |
+
"model.layers.1.mlp.down_proj.weight": "pytorch_model-00002-of-00023.bin",
|
| 19 |
+
"model.layers.1.mlp.gate_proj.weight": "pytorch_model-00002-of-00023.bin",
|
| 20 |
+
"model.layers.1.mlp.up_proj.weight": "pytorch_model-00002-of-00023.bin",
|
| 21 |
+
"model.layers.1.post_attention_layernorm.weight": "pytorch_model-00002-of-00023.bin",
|
| 22 |
+
"model.layers.1.self_attn.k_proj.weight": "pytorch_model-00002-of-00023.bin",
|
| 23 |
+
"model.layers.1.self_attn.o_proj.weight": "pytorch_model-00002-of-00023.bin",
|
| 24 |
+
"model.layers.1.self_attn.q_proj.weight": "pytorch_model-00002-of-00023.bin",
|
| 25 |
+
"model.layers.1.self_attn.v_proj.weight": "pytorch_model-00002-of-00023.bin",
|
| 26 |
+
"model.layers.10.input_layernorm.weight": "pytorch_model-00008-of-00023.bin",
|
| 27 |
+
"model.layers.10.mlp.down_proj.weight": "pytorch_model-00008-of-00023.bin",
|
| 28 |
+
"model.layers.10.mlp.gate_proj.weight": "pytorch_model-00008-of-00023.bin",
|
| 29 |
+
"model.layers.10.mlp.up_proj.weight": "pytorch_model-00008-of-00023.bin",
|
| 30 |
+
"model.layers.10.post_attention_layernorm.weight": "pytorch_model-00008-of-00023.bin",
|
| 31 |
+
"model.layers.10.self_attn.k_proj.weight": "pytorch_model-00008-of-00023.bin",
|
| 32 |
+
"model.layers.10.self_attn.o_proj.weight": "pytorch_model-00008-of-00023.bin",
|
| 33 |
+
"model.layers.10.self_attn.q_proj.weight": "pytorch_model-00008-of-00023.bin",
|
| 34 |
+
"model.layers.10.self_attn.v_proj.weight": "pytorch_model-00008-of-00023.bin",
|
| 35 |
+
"model.layers.11.input_layernorm.weight": "pytorch_model-00009-of-00023.bin",
|
| 36 |
+
"model.layers.11.mlp.down_proj.weight": "pytorch_model-00009-of-00023.bin",
|
| 37 |
+
"model.layers.11.mlp.gate_proj.weight": "pytorch_model-00009-of-00023.bin",
|
| 38 |
+
"model.layers.11.mlp.up_proj.weight": "pytorch_model-00009-of-00023.bin",
|
| 39 |
+
"model.layers.11.post_attention_layernorm.weight": "pytorch_model-00009-of-00023.bin",
|
| 40 |
+
"model.layers.11.self_attn.k_proj.weight": "pytorch_model-00008-of-00023.bin",
|
| 41 |
+
"model.layers.11.self_attn.o_proj.weight": "pytorch_model-00008-of-00023.bin",
|
| 42 |
+
"model.layers.11.self_attn.q_proj.weight": "pytorch_model-00008-of-00023.bin",
|
| 43 |
+
"model.layers.11.self_attn.v_proj.weight": "pytorch_model-00008-of-00023.bin",
|
| 44 |
+
"model.layers.12.input_layernorm.weight": "pytorch_model-00010-of-00023.bin",
|
| 45 |
+
"model.layers.12.mlp.down_proj.weight": "pytorch_model-00010-of-00023.bin",
|
| 46 |
+
"model.layers.12.mlp.gate_proj.weight": "pytorch_model-00009-of-00023.bin",
|
| 47 |
+
"model.layers.12.mlp.up_proj.weight": "pytorch_model-00009-of-00023.bin",
|
| 48 |
+
"model.layers.12.post_attention_layernorm.weight": "pytorch_model-00010-of-00023.bin",
|
| 49 |
+
"model.layers.12.self_attn.k_proj.weight": "pytorch_model-00009-of-00023.bin",
|
| 50 |
+
"model.layers.12.self_attn.o_proj.weight": "pytorch_model-00009-of-00023.bin",
|
| 51 |
+
"model.layers.12.self_attn.q_proj.weight": "pytorch_model-00009-of-00023.bin",
|
| 52 |
+
"model.layers.12.self_attn.v_proj.weight": "pytorch_model-00009-of-00023.bin",
|
| 53 |
+
"model.layers.13.input_layernorm.weight": "pytorch_model-00010-of-00023.bin",
|
| 54 |
+
"model.layers.13.mlp.down_proj.weight": "pytorch_model-00010-of-00023.bin",
|
| 55 |
+
"model.layers.13.mlp.gate_proj.weight": "pytorch_model-00010-of-00023.bin",
|
| 56 |
+
"model.layers.13.mlp.up_proj.weight": "pytorch_model-00010-of-00023.bin",
|
| 57 |
+
"model.layers.13.post_attention_layernorm.weight": "pytorch_model-00010-of-00023.bin",
|
| 58 |
+
"model.layers.13.self_attn.k_proj.weight": "pytorch_model-00010-of-00023.bin",
|
| 59 |
+
"model.layers.13.self_attn.o_proj.weight": "pytorch_model-00010-of-00023.bin",
|
| 60 |
+
"model.layers.13.self_attn.q_proj.weight": "pytorch_model-00010-of-00023.bin",
|
| 61 |
+
"model.layers.13.self_attn.v_proj.weight": "pytorch_model-00010-of-00023.bin",
|
| 62 |
+
"model.layers.14.input_layernorm.weight": "pytorch_model-00011-of-00023.bin",
|
| 63 |
+
"model.layers.14.mlp.down_proj.weight": "pytorch_model-00011-of-00023.bin",
|
| 64 |
+
"model.layers.14.mlp.gate_proj.weight": "pytorch_model-00011-of-00023.bin",
|
| 65 |
+
"model.layers.14.mlp.up_proj.weight": "pytorch_model-00011-of-00023.bin",
|
| 66 |
+
"model.layers.14.post_attention_layernorm.weight": "pytorch_model-00011-of-00023.bin",
|
| 67 |
+
"model.layers.14.self_attn.k_proj.weight": "pytorch_model-00010-of-00023.bin",
|
| 68 |
+
"model.layers.14.self_attn.o_proj.weight": "pytorch_model-00010-of-00023.bin",
|
| 69 |
+
"model.layers.14.self_attn.q_proj.weight": "pytorch_model-00010-of-00023.bin",
|
| 70 |
+
"model.layers.14.self_attn.v_proj.weight": "pytorch_model-00010-of-00023.bin",
|
| 71 |
+
"model.layers.15.input_layernorm.weight": "pytorch_model-00012-of-00023.bin",
|
| 72 |
+
"model.layers.15.mlp.down_proj.weight": "pytorch_model-00012-of-00023.bin",
|
| 73 |
+
"model.layers.15.mlp.gate_proj.weight": "pytorch_model-00011-of-00023.bin",
|
| 74 |
+
"model.layers.15.mlp.up_proj.weight": "pytorch_model-00011-of-00023.bin",
|
| 75 |
+
"model.layers.15.post_attention_layernorm.weight": "pytorch_model-00012-of-00023.bin",
|
| 76 |
+
"model.layers.15.self_attn.k_proj.weight": "pytorch_model-00011-of-00023.bin",
|
| 77 |
+
"model.layers.15.self_attn.o_proj.weight": "pytorch_model-00011-of-00023.bin",
|
| 78 |
+
"model.layers.15.self_attn.q_proj.weight": "pytorch_model-00011-of-00023.bin",
|
| 79 |
+
"model.layers.15.self_attn.v_proj.weight": "pytorch_model-00011-of-00023.bin",
|
| 80 |
+
"model.layers.16.input_layernorm.weight": "pytorch_model-00012-of-00023.bin",
|
| 81 |
+
"model.layers.16.mlp.down_proj.weight": "pytorch_model-00012-of-00023.bin",
|
| 82 |
+
"model.layers.16.mlp.gate_proj.weight": "pytorch_model-00012-of-00023.bin",
|
| 83 |
+
"model.layers.16.mlp.up_proj.weight": "pytorch_model-00012-of-00023.bin",
|
| 84 |
+
"model.layers.16.post_attention_layernorm.weight": "pytorch_model-00012-of-00023.bin",
|
| 85 |
+
"model.layers.16.self_attn.k_proj.weight": "pytorch_model-00012-of-00023.bin",
|
| 86 |
+
"model.layers.16.self_attn.o_proj.weight": "pytorch_model-00012-of-00023.bin",
|
| 87 |
+
"model.layers.16.self_attn.q_proj.weight": "pytorch_model-00012-of-00023.bin",
|
| 88 |
+
"model.layers.16.self_attn.v_proj.weight": "pytorch_model-00012-of-00023.bin",
|
| 89 |
+
"model.layers.17.input_layernorm.weight": "pytorch_model-00013-of-00023.bin",
|
| 90 |
+
"model.layers.17.mlp.down_proj.weight": "pytorch_model-00013-of-00023.bin",
|
| 91 |
+
"model.layers.17.mlp.gate_proj.weight": "pytorch_model-00013-of-00023.bin",
|
| 92 |
+
"model.layers.17.mlp.up_proj.weight": "pytorch_model-00013-of-00023.bin",
|
| 93 |
+
"model.layers.17.post_attention_layernorm.weight": "pytorch_model-00013-of-00023.bin",
|
| 94 |
+
"model.layers.17.self_attn.k_proj.weight": "pytorch_model-00012-of-00023.bin",
|
| 95 |
+
"model.layers.17.self_attn.o_proj.weight": "pytorch_model-00012-of-00023.bin",
|
| 96 |
+
"model.layers.17.self_attn.q_proj.weight": "pytorch_model-00012-of-00023.bin",
|
| 97 |
+
"model.layers.17.self_attn.v_proj.weight": "pytorch_model-00012-of-00023.bin",
|
| 98 |
+
"model.layers.18.input_layernorm.weight": "pytorch_model-00014-of-00023.bin",
|
| 99 |
+
"model.layers.18.mlp.down_proj.weight": "pytorch_model-00014-of-00023.bin",
|
| 100 |
+
"model.layers.18.mlp.gate_proj.weight": "pytorch_model-00013-of-00023.bin",
|
| 101 |
+
"model.layers.18.mlp.up_proj.weight": "pytorch_model-00013-of-00023.bin",
|
| 102 |
+
"model.layers.18.post_attention_layernorm.weight": "pytorch_model-00014-of-00023.bin",
|
| 103 |
+
"model.layers.18.self_attn.k_proj.weight": "pytorch_model-00013-of-00023.bin",
|
| 104 |
+
"model.layers.18.self_attn.o_proj.weight": "pytorch_model-00013-of-00023.bin",
|
| 105 |
+
"model.layers.18.self_attn.q_proj.weight": "pytorch_model-00013-of-00023.bin",
|
| 106 |
+
"model.layers.18.self_attn.v_proj.weight": "pytorch_model-00013-of-00023.bin",
|
| 107 |
+
"model.layers.19.input_layernorm.weight": "pytorch_model-00014-of-00023.bin",
|
| 108 |
+
"model.layers.19.mlp.down_proj.weight": "pytorch_model-00014-of-00023.bin",
|
| 109 |
+
"model.layers.19.mlp.gate_proj.weight": "pytorch_model-00014-of-00023.bin",
|
| 110 |
+
"model.layers.19.mlp.up_proj.weight": "pytorch_model-00014-of-00023.bin",
|
| 111 |
+
"model.layers.19.post_attention_layernorm.weight": "pytorch_model-00014-of-00023.bin",
|
| 112 |
+
"model.layers.19.self_attn.k_proj.weight": "pytorch_model-00014-of-00023.bin",
|
| 113 |
+
"model.layers.19.self_attn.o_proj.weight": "pytorch_model-00014-of-00023.bin",
|
| 114 |
+
"model.layers.19.self_attn.q_proj.weight": "pytorch_model-00014-of-00023.bin",
|
| 115 |
+
"model.layers.19.self_attn.v_proj.weight": "pytorch_model-00014-of-00023.bin",
|
| 116 |
+
"model.layers.2.input_layernorm.weight": "pytorch_model-00003-of-00023.bin",
|
| 117 |
+
"model.layers.2.mlp.down_proj.weight": "pytorch_model-00003-of-00023.bin",
|
| 118 |
+
"model.layers.2.mlp.gate_proj.weight": "pytorch_model-00003-of-00023.bin",
|
| 119 |
+
"model.layers.2.mlp.up_proj.weight": "pytorch_model-00003-of-00023.bin",
|
| 120 |
+
"model.layers.2.post_attention_layernorm.weight": "pytorch_model-00003-of-00023.bin",
|
| 121 |
+
"model.layers.2.self_attn.k_proj.weight": "pytorch_model-00002-of-00023.bin",
|
| 122 |
+
"model.layers.2.self_attn.o_proj.weight": "pytorch_model-00002-of-00023.bin",
|
| 123 |
+
"model.layers.2.self_attn.q_proj.weight": "pytorch_model-00002-of-00023.bin",
|
| 124 |
+
"model.layers.2.self_attn.v_proj.weight": "pytorch_model-00002-of-00023.bin",
|
| 125 |
+
"model.layers.20.input_layernorm.weight": "pytorch_model-00015-of-00023.bin",
|
| 126 |
+
"model.layers.20.mlp.down_proj.weight": "pytorch_model-00015-of-00023.bin",
|
| 127 |
+
"model.layers.20.mlp.gate_proj.weight": "pytorch_model-00015-of-00023.bin",
|
| 128 |
+
"model.layers.20.mlp.up_proj.weight": "pytorch_model-00015-of-00023.bin",
|
| 129 |
+
"model.layers.20.post_attention_layernorm.weight": "pytorch_model-00015-of-00023.bin",
|
| 130 |
+
"model.layers.20.self_attn.k_proj.weight": "pytorch_model-00014-of-00023.bin",
|
| 131 |
+
"model.layers.20.self_attn.o_proj.weight": "pytorch_model-00014-of-00023.bin",
|
| 132 |
+
"model.layers.20.self_attn.q_proj.weight": "pytorch_model-00014-of-00023.bin",
|
| 133 |
+
"model.layers.20.self_attn.v_proj.weight": "pytorch_model-00014-of-00023.bin",
|
| 134 |
+
"model.layers.21.input_layernorm.weight": "pytorch_model-00016-of-00023.bin",
|
| 135 |
+
"model.layers.21.mlp.down_proj.weight": "pytorch_model-00016-of-00023.bin",
|
| 136 |
+
"model.layers.21.mlp.gate_proj.weight": "pytorch_model-00015-of-00023.bin",
|
| 137 |
+
"model.layers.21.mlp.up_proj.weight": "pytorch_model-00015-of-00023.bin",
|
| 138 |
+
"model.layers.21.post_attention_layernorm.weight": "pytorch_model-00016-of-00023.bin",
|
| 139 |
+
"model.layers.21.self_attn.k_proj.weight": "pytorch_model-00015-of-00023.bin",
|
| 140 |
+
"model.layers.21.self_attn.o_proj.weight": "pytorch_model-00015-of-00023.bin",
|
| 141 |
+
"model.layers.21.self_attn.q_proj.weight": "pytorch_model-00015-of-00023.bin",
|
| 142 |
+
"model.layers.21.self_attn.v_proj.weight": "pytorch_model-00015-of-00023.bin",
|
| 143 |
+
"model.layers.22.input_layernorm.weight": "pytorch_model-00016-of-00023.bin",
|
| 144 |
+
"model.layers.22.mlp.down_proj.weight": "pytorch_model-00016-of-00023.bin",
|
| 145 |
+
"model.layers.22.mlp.gate_proj.weight": "pytorch_model-00016-of-00023.bin",
|
| 146 |
+
"model.layers.22.mlp.up_proj.weight": "pytorch_model-00016-of-00023.bin",
|
| 147 |
+
"model.layers.22.post_attention_layernorm.weight": "pytorch_model-00016-of-00023.bin",
|
| 148 |
+
"model.layers.22.self_attn.k_proj.weight": "pytorch_model-00016-of-00023.bin",
|
| 149 |
+
"model.layers.22.self_attn.o_proj.weight": "pytorch_model-00016-of-00023.bin",
|
| 150 |
+
"model.layers.22.self_attn.q_proj.weight": "pytorch_model-00016-of-00023.bin",
|
| 151 |
+
"model.layers.22.self_attn.v_proj.weight": "pytorch_model-00016-of-00023.bin",
|
| 152 |
+
"model.layers.23.input_layernorm.weight": "pytorch_model-00017-of-00023.bin",
|
| 153 |
+
"model.layers.23.mlp.down_proj.weight": "pytorch_model-00017-of-00023.bin",
|
| 154 |
+
"model.layers.23.mlp.gate_proj.weight": "pytorch_model-00017-of-00023.bin",
|
| 155 |
+
"model.layers.23.mlp.up_proj.weight": "pytorch_model-00017-of-00023.bin",
|
| 156 |
+
"model.layers.23.post_attention_layernorm.weight": "pytorch_model-00017-of-00023.bin",
|
| 157 |
+
"model.layers.23.self_attn.k_proj.weight": "pytorch_model-00016-of-00023.bin",
|
| 158 |
+
"model.layers.23.self_attn.o_proj.weight": "pytorch_model-00016-of-00023.bin",
|
| 159 |
+
"model.layers.23.self_attn.q_proj.weight": "pytorch_model-00016-of-00023.bin",
|
| 160 |
+
"model.layers.23.self_attn.v_proj.weight": "pytorch_model-00016-of-00023.bin",
|
| 161 |
+
"model.layers.24.input_layernorm.weight": "pytorch_model-00018-of-00023.bin",
|
| 162 |
+
"model.layers.24.mlp.down_proj.weight": "pytorch_model-00018-of-00023.bin",
|
| 163 |
+
"model.layers.24.mlp.gate_proj.weight": "pytorch_model-00017-of-00023.bin",
|
| 164 |
+
"model.layers.24.mlp.up_proj.weight": "pytorch_model-00017-of-00023.bin",
|
| 165 |
+
"model.layers.24.post_attention_layernorm.weight": "pytorch_model-00018-of-00023.bin",
|
| 166 |
+
"model.layers.24.self_attn.k_proj.weight": "pytorch_model-00017-of-00023.bin",
|
| 167 |
+
"model.layers.24.self_attn.o_proj.weight": "pytorch_model-00017-of-00023.bin",
|
| 168 |
+
"model.layers.24.self_attn.q_proj.weight": "pytorch_model-00017-of-00023.bin",
|
| 169 |
+
"model.layers.24.self_attn.v_proj.weight": "pytorch_model-00017-of-00023.bin",
|
| 170 |
+
"model.layers.25.input_layernorm.weight": "pytorch_model-00018-of-00023.bin",
|
| 171 |
+
"model.layers.25.mlp.down_proj.weight": "pytorch_model-00018-of-00023.bin",
|
| 172 |
+
"model.layers.25.mlp.gate_proj.weight": "pytorch_model-00018-of-00023.bin",
|
| 173 |
+
"model.layers.25.mlp.up_proj.weight": "pytorch_model-00018-of-00023.bin",
|
| 174 |
+
"model.layers.25.post_attention_layernorm.weight": "pytorch_model-00018-of-00023.bin",
|
| 175 |
+
"model.layers.25.self_attn.k_proj.weight": "pytorch_model-00018-of-00023.bin",
|
| 176 |
+
"model.layers.25.self_attn.o_proj.weight": "pytorch_model-00018-of-00023.bin",
|
| 177 |
+
"model.layers.25.self_attn.q_proj.weight": "pytorch_model-00018-of-00023.bin",
|
| 178 |
+
"model.layers.25.self_attn.v_proj.weight": "pytorch_model-00018-of-00023.bin",
|
| 179 |
+
"model.layers.26.input_layernorm.weight": "pytorch_model-00019-of-00023.bin",
|
| 180 |
+
"model.layers.26.mlp.down_proj.weight": "pytorch_model-00019-of-00023.bin",
|
| 181 |
+
"model.layers.26.mlp.gate_proj.weight": "pytorch_model-00019-of-00023.bin",
|
| 182 |
+
"model.layers.26.mlp.up_proj.weight": "pytorch_model-00019-of-00023.bin",
|
| 183 |
+
"model.layers.26.post_attention_layernorm.weight": "pytorch_model-00019-of-00023.bin",
|
| 184 |
+
"model.layers.26.self_attn.k_proj.weight": "pytorch_model-00018-of-00023.bin",
|
| 185 |
+
"model.layers.26.self_attn.o_proj.weight": "pytorch_model-00018-of-00023.bin",
|
| 186 |
+
"model.layers.26.self_attn.q_proj.weight": "pytorch_model-00018-of-00023.bin",
|
| 187 |
+
"model.layers.26.self_attn.v_proj.weight": "pytorch_model-00018-of-00023.bin",
|
| 188 |
+
"model.layers.27.input_layernorm.weight": "pytorch_model-00020-of-00023.bin",
|
| 189 |
+
"model.layers.27.mlp.down_proj.weight": "pytorch_model-00020-of-00023.bin",
|
| 190 |
+
"model.layers.27.mlp.gate_proj.weight": "pytorch_model-00019-of-00023.bin",
|
| 191 |
+
"model.layers.27.mlp.up_proj.weight": "pytorch_model-00019-of-00023.bin",
|
| 192 |
+
"model.layers.27.post_attention_layernorm.weight": "pytorch_model-00020-of-00023.bin",
|
| 193 |
+
"model.layers.27.self_attn.k_proj.weight": "pytorch_model-00019-of-00023.bin",
|
| 194 |
+
"model.layers.27.self_attn.o_proj.weight": "pytorch_model-00019-of-00023.bin",
|
| 195 |
+
"model.layers.27.self_attn.q_proj.weight": "pytorch_model-00019-of-00023.bin",
|
| 196 |
+
"model.layers.27.self_attn.v_proj.weight": "pytorch_model-00019-of-00023.bin",
|
| 197 |
+
"model.layers.28.input_layernorm.weight": "pytorch_model-00020-of-00023.bin",
|
| 198 |
+
"model.layers.28.mlp.down_proj.weight": "pytorch_model-00020-of-00023.bin",
|
| 199 |
+
"model.layers.28.mlp.gate_proj.weight": "pytorch_model-00020-of-00023.bin",
|
| 200 |
+
"model.layers.28.mlp.up_proj.weight": "pytorch_model-00020-of-00023.bin",
|
| 201 |
+
"model.layers.28.post_attention_layernorm.weight": "pytorch_model-00020-of-00023.bin",
|
| 202 |
+
"model.layers.28.self_attn.k_proj.weight": "pytorch_model-00020-of-00023.bin",
|
| 203 |
+
"model.layers.28.self_attn.o_proj.weight": "pytorch_model-00020-of-00023.bin",
|
| 204 |
+
"model.layers.28.self_attn.q_proj.weight": "pytorch_model-00020-of-00023.bin",
|
| 205 |
+
"model.layers.28.self_attn.v_proj.weight": "pytorch_model-00020-of-00023.bin",
|
| 206 |
+
"model.layers.29.input_layernorm.weight": "pytorch_model-00021-of-00023.bin",
|
| 207 |
+
"model.layers.29.mlp.down_proj.weight": "pytorch_model-00021-of-00023.bin",
|
| 208 |
+
"model.layers.29.mlp.gate_proj.weight": "pytorch_model-00021-of-00023.bin",
|
| 209 |
+
"model.layers.29.mlp.up_proj.weight": "pytorch_model-00021-of-00023.bin",
|
| 210 |
+
"model.layers.29.post_attention_layernorm.weight": "pytorch_model-00021-of-00023.bin",
|
| 211 |
+
"model.layers.29.self_attn.k_proj.weight": "pytorch_model-00020-of-00023.bin",
|
| 212 |
+
"model.layers.29.self_attn.o_proj.weight": "pytorch_model-00020-of-00023.bin",
|
| 213 |
+
"model.layers.29.self_attn.q_proj.weight": "pytorch_model-00020-of-00023.bin",
|
| 214 |
+
"model.layers.29.self_attn.v_proj.weight": "pytorch_model-00020-of-00023.bin",
|
| 215 |
+
"model.layers.3.input_layernorm.weight": "pytorch_model-00004-of-00023.bin",
|
| 216 |
+
"model.layers.3.mlp.down_proj.weight": "pytorch_model-00004-of-00023.bin",
|
| 217 |
+
"model.layers.3.mlp.gate_proj.weight": "pytorch_model-00003-of-00023.bin",
|
| 218 |
+
"model.layers.3.mlp.up_proj.weight": "pytorch_model-00003-of-00023.bin",
|
| 219 |
+
"model.layers.3.post_attention_layernorm.weight": "pytorch_model-00004-of-00023.bin",
|
| 220 |
+
"model.layers.3.self_attn.k_proj.weight": "pytorch_model-00003-of-00023.bin",
|
| 221 |
+
"model.layers.3.self_attn.o_proj.weight": "pytorch_model-00003-of-00023.bin",
|
| 222 |
+
"model.layers.3.self_attn.q_proj.weight": "pytorch_model-00003-of-00023.bin",
|
| 223 |
+
"model.layers.3.self_attn.v_proj.weight": "pytorch_model-00003-of-00023.bin",
|
| 224 |
+
"model.layers.30.input_layernorm.weight": "pytorch_model-00022-of-00023.bin",
|
| 225 |
+
"model.layers.30.mlp.down_proj.weight": "pytorch_model-00022-of-00023.bin",
|
| 226 |
+
"model.layers.30.mlp.gate_proj.weight": "pytorch_model-00021-of-00023.bin",
|
| 227 |
+
"model.layers.30.mlp.up_proj.weight": "pytorch_model-00021-of-00023.bin",
|
| 228 |
+
"model.layers.30.post_attention_layernorm.weight": "pytorch_model-00022-of-00023.bin",
|
| 229 |
+
"model.layers.30.self_attn.k_proj.weight": "pytorch_model-00021-of-00023.bin",
|
| 230 |
+
"model.layers.30.self_attn.o_proj.weight": "pytorch_model-00021-of-00023.bin",
|
| 231 |
+
"model.layers.30.self_attn.q_proj.weight": "pytorch_model-00021-of-00023.bin",
|
| 232 |
+
"model.layers.30.self_attn.v_proj.weight": "pytorch_model-00021-of-00023.bin",
|
| 233 |
+
"model.layers.31.input_layernorm.weight": "pytorch_model-00022-of-00023.bin",
|
| 234 |
+
"model.layers.31.mlp.down_proj.weight": "pytorch_model-00022-of-00023.bin",
|
| 235 |
+
"model.layers.31.mlp.gate_proj.weight": "pytorch_model-00022-of-00023.bin",
|
| 236 |
+
"model.layers.31.mlp.up_proj.weight": "pytorch_model-00022-of-00023.bin",
|
| 237 |
+
"model.layers.31.post_attention_layernorm.weight": "pytorch_model-00022-of-00023.bin",
|
| 238 |
+
"model.layers.31.self_attn.k_proj.weight": "pytorch_model-00022-of-00023.bin",
|
| 239 |
+
"model.layers.31.self_attn.o_proj.weight": "pytorch_model-00022-of-00023.bin",
|
| 240 |
+
"model.layers.31.self_attn.q_proj.weight": "pytorch_model-00022-of-00023.bin",
|
| 241 |
+
"model.layers.31.self_attn.v_proj.weight": "pytorch_model-00022-of-00023.bin",
|
| 242 |
+
"model.layers.4.input_layernorm.weight": "pytorch_model-00004-of-00023.bin",
|
| 243 |
+
"model.layers.4.mlp.down_proj.weight": "pytorch_model-00004-of-00023.bin",
|
| 244 |
+
"model.layers.4.mlp.gate_proj.weight": "pytorch_model-00004-of-00023.bin",
|
| 245 |
+
"model.layers.4.mlp.up_proj.weight": "pytorch_model-00004-of-00023.bin",
|
| 246 |
+
"model.layers.4.post_attention_layernorm.weight": "pytorch_model-00004-of-00023.bin",
|
| 247 |
+
"model.layers.4.self_attn.k_proj.weight": "pytorch_model-00004-of-00023.bin",
|
| 248 |
+
"model.layers.4.self_attn.o_proj.weight": "pytorch_model-00004-of-00023.bin",
|
| 249 |
+
"model.layers.4.self_attn.q_proj.weight": "pytorch_model-00004-of-00023.bin",
|
| 250 |
+
"model.layers.4.self_attn.v_proj.weight": "pytorch_model-00004-of-00023.bin",
|
| 251 |
+
"model.layers.5.input_layernorm.weight": "pytorch_model-00005-of-00023.bin",
|
| 252 |
+
"model.layers.5.mlp.down_proj.weight": "pytorch_model-00005-of-00023.bin",
|
| 253 |
+
"model.layers.5.mlp.gate_proj.weight": "pytorch_model-00005-of-00023.bin",
|
| 254 |
+
"model.layers.5.mlp.up_proj.weight": "pytorch_model-00005-of-00023.bin",
|
| 255 |
+
"model.layers.5.post_attention_layernorm.weight": "pytorch_model-00005-of-00023.bin",
|
| 256 |
+
"model.layers.5.self_attn.k_proj.weight": "pytorch_model-00004-of-00023.bin",
|
| 257 |
+
"model.layers.5.self_attn.o_proj.weight": "pytorch_model-00004-of-00023.bin",
|
| 258 |
+
"model.layers.5.self_attn.q_proj.weight": "pytorch_model-00004-of-00023.bin",
|
| 259 |
+
"model.layers.5.self_attn.v_proj.weight": "pytorch_model-00004-of-00023.bin",
|
| 260 |
+
"model.layers.6.input_layernorm.weight": "pytorch_model-00006-of-00023.bin",
|
| 261 |
+
"model.layers.6.mlp.down_proj.weight": "pytorch_model-00006-of-00023.bin",
|
| 262 |
+
"model.layers.6.mlp.gate_proj.weight": "pytorch_model-00005-of-00023.bin",
|
| 263 |
+
"model.layers.6.mlp.up_proj.weight": "pytorch_model-00005-of-00023.bin",
|
| 264 |
+
"model.layers.6.post_attention_layernorm.weight": "pytorch_model-00006-of-00023.bin",
|
| 265 |
+
"model.layers.6.self_attn.k_proj.weight": "pytorch_model-00005-of-00023.bin",
|
| 266 |
+
"model.layers.6.self_attn.o_proj.weight": "pytorch_model-00005-of-00023.bin",
|
| 267 |
+
"model.layers.6.self_attn.q_proj.weight": "pytorch_model-00005-of-00023.bin",
|
| 268 |
+
"model.layers.6.self_attn.v_proj.weight": "pytorch_model-00005-of-00023.bin",
|
| 269 |
+
"model.layers.7.input_layernorm.weight": "pytorch_model-00006-of-00023.bin",
|
| 270 |
+
"model.layers.7.mlp.down_proj.weight": "pytorch_model-00006-of-00023.bin",
|
| 271 |
+
"model.layers.7.mlp.gate_proj.weight": "pytorch_model-00006-of-00023.bin",
|
| 272 |
+
"model.layers.7.mlp.up_proj.weight": "pytorch_model-00006-of-00023.bin",
|
| 273 |
+
"model.layers.7.post_attention_layernorm.weight": "pytorch_model-00006-of-00023.bin",
|
| 274 |
+
"model.layers.7.self_attn.k_proj.weight": "pytorch_model-00006-of-00023.bin",
|
| 275 |
+
"model.layers.7.self_attn.o_proj.weight": "pytorch_model-00006-of-00023.bin",
|
| 276 |
+
"model.layers.7.self_attn.q_proj.weight": "pytorch_model-00006-of-00023.bin",
|
| 277 |
+
"model.layers.7.self_attn.v_proj.weight": "pytorch_model-00006-of-00023.bin",
|
| 278 |
+
"model.layers.8.input_layernorm.weight": "pytorch_model-00007-of-00023.bin",
|
| 279 |
+
"model.layers.8.mlp.down_proj.weight": "pytorch_model-00007-of-00023.bin",
|
| 280 |
+
"model.layers.8.mlp.gate_proj.weight": "pytorch_model-00007-of-00023.bin",
|
| 281 |
+
"model.layers.8.mlp.up_proj.weight": "pytorch_model-00007-of-00023.bin",
|
| 282 |
+
"model.layers.8.post_attention_layernorm.weight": "pytorch_model-00007-of-00023.bin",
|
| 283 |
+
"model.layers.8.self_attn.k_proj.weight": "pytorch_model-00006-of-00023.bin",
|
| 284 |
+
"model.layers.8.self_attn.o_proj.weight": "pytorch_model-00006-of-00023.bin",
|
| 285 |
+
"model.layers.8.self_attn.q_proj.weight": "pytorch_model-00006-of-00023.bin",
|
| 286 |
+
"model.layers.8.self_attn.v_proj.weight": "pytorch_model-00006-of-00023.bin",
|
| 287 |
+
"model.layers.9.input_layernorm.weight": "pytorch_model-00008-of-00023.bin",
|
| 288 |
+
"model.layers.9.mlp.down_proj.weight": "pytorch_model-00008-of-00023.bin",
|
| 289 |
+
"model.layers.9.mlp.gate_proj.weight": "pytorch_model-00007-of-00023.bin",
|
| 290 |
+
"model.layers.9.mlp.up_proj.weight": "pytorch_model-00007-of-00023.bin",
|
| 291 |
+
"model.layers.9.post_attention_layernorm.weight": "pytorch_model-00008-of-00023.bin",
|
| 292 |
+
"model.layers.9.self_attn.k_proj.weight": "pytorch_model-00007-of-00023.bin",
|
| 293 |
+
"model.layers.9.self_attn.o_proj.weight": "pytorch_model-00007-of-00023.bin",
|
| 294 |
+
"model.layers.9.self_attn.q_proj.weight": "pytorch_model-00007-of-00023.bin",
|
| 295 |
+
"model.layers.9.self_attn.v_proj.weight": "pytorch_model-00007-of-00023.bin",
|
| 296 |
+
"model.norm.weight": "pytorch_model-00022-of-00023.bin"
|
| 297 |
+
}
|
| 298 |
+
}
|