Hugging Face's logo

ybelkada
/
fuyu-8b-sharded

Text Generation
Transformers
PyTorch
Safetensors
fuyu
Inference Endpoints
Model card Files Community
2
ybelkada commited on
Commit
f29f9f0
•
1 Parent(s): d6c010e

Upload FuyuForCausalLM

Browse files
Files changed (14) hide show
  1. config.json +34 -0
  2. generation_config.json +6 -0
  3. pytorch_model-00001-of-00011.bin +3 -0
  4. pytorch_model-00002-of-00011.bin +3 -0
  5. pytorch_model-00003-of-00011.bin +3 -0
  6. pytorch_model-00004-of-00011.bin +3 -0
  7. pytorch_model-00005-of-00011.bin +3 -0
  8. pytorch_model-00006-of-00011.bin +3 -0
  9. pytorch_model-00007-of-00011.bin +3 -0
  10. pytorch_model-00008-of-00011.bin +3 -0
  11. pytorch_model-00009-of-00011.bin +3 -0
  12. pytorch_model-00010-of-00011.bin +3 -0
  13. pytorch_model-00011-of-00011.bin +3 -0
  14. pytorch_model.bin.index.json +589 -0
config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "adept/fuyu-8b",
3
+ "architectures": [
4
+ "FuyuForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 71013,
9
+ "hidden_act": "relu2",
10
+ "hidden_dropout": 0.0,
11
+ "hidden_size": 4096,
12
+ "image_size": 300,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 16384,
15
+ "layer_norm_eps": 1e-05,
16
+ "max_position_embeddings": 16384,
17
+ "model_type": "fuyu",
18
+ "num_attention_heads": 64,
19
+ "num_channels": 3,
20
+ "num_hidden_layers": 36,
21
+ "partial_rotary_factor": 0.5,
22
+ "patch_size": 30,
23
+ "qk_layernorm": true,
24
+ "rope_scaling": null,
25
+ "rope_theta": 25000.0,
26
+ "text_config": {
27
+ "model_type": "persimmon"
28
+ },
29
+ "tie_word_embeddings": false,
30
+ "torch_dtype": "bfloat16",
31
+ "transformers_version": "4.35.0.dev0",
32
+ "use_cache": true,
33
+ "vocab_size": 262144
34
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 71013,
5
+ "transformers_version": "4.35.0.dev0"
6
+ }
pytorch_model-00001-of-00011.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3a96eaca445974eb7b73608fa6f966a31f549e6e343fe5e3af3ecfb4769a177
3
+ size 2147485061
pytorch_model-00002-of-00011.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe5d7b5650f94b1ae198748b1c3a9f5c8764eb113f21ab7b872377f9242b1783
3
+ size 1879569566
pytorch_model-00003-of-00011.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:082de81a78d0d832fbdadbcdba37138937f1281099a9cff0d37fb17dde61a81f
3
+ size 1879579174
pytorch_model-00004-of-00011.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4adbde4cd112bfef10c01b35130385d4cae5f7872720e9726aa706d395c1a15
3
+ size 1980265182
pytorch_model-00005-of-00011.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91650fe9a4cdaa0e517a7bcb0bfcb63ea4016e8080314ffd9412201e6acbcb5f
3
+ size 1913141862
pytorch_model-00006-of-00011.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e64d517f12d1f1c2cf29f055ba480cbe0000978f6e887d2b7d2a974026e491e6
3
+ size 1879569630
pytorch_model-00007-of-00011.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:431731e805d7b6eff43578a35b69f3c9e28edac2d8a944ac4845c0acc989b88c
3
+ size 1879579238
pytorch_model-00008-of-00011.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:282f7105957299dbf3a760005991907ff89728ca7ea22b37fe13cd957d948ee6
3
+ size 1980265182
pytorch_model-00009-of-00011.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e353dcf91f3a1c40d2dfe23da7e7f3d42e26650b45746f4c4207ff2702c2dbad
3
+ size 1107626890
pytorch_model-00010-of-00011.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fdbe5609f7ffedaa27a2d9174ae4161929dd143c2423887b3269d147775dadf2
3
+ size 2147485061
pytorch_model-00011-of-00011.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d185f22240c5a1cbc1b6dbadb3c5cd3e1b9edd9bf977a770d13e991b65faafd
3
+ size 22128342
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,589 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 18816477184
4
+ },
5
+ "weight_map": {
6
+ "language_model.lm_head.weight": "pytorch_model-00010-of-00011.bin",
7
+ "language_model.model.embed_tokens.weight": "pytorch_model-00001-of-00011.bin",
8
+ "language_model.model.final_layernorm.bias": "pytorch_model-00009-of-00011.bin",
9
+ "language_model.model.final_layernorm.weight": "pytorch_model-00009-of-00011.bin",
10
+ "language_model.model.layers.0.input_layernorm.bias": "pytorch_model-00002-of-00011.bin",
11
+ "language_model.model.layers.0.input_layernorm.weight": "pytorch_model-00002-of-00011.bin",
12
+ "language_model.model.layers.0.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00011.bin",
13
+ "language_model.model.layers.0.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00011.bin",
14
+ "language_model.model.layers.0.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00011.bin",
15
+ "language_model.model.layers.0.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00011.bin",
16
+ "language_model.model.layers.0.post_attention_layernorm.bias": "pytorch_model-00002-of-00011.bin",
17
+ "language_model.model.layers.0.post_attention_layernorm.weight": "pytorch_model-00002-of-00011.bin",
18
+ "language_model.model.layers.0.self_attn.dense.bias": "pytorch_model-00002-of-00011.bin",
19
+ "language_model.model.layers.0.self_attn.dense.weight": "pytorch_model-00002-of-00011.bin",
20
+ "language_model.model.layers.0.self_attn.k_layernorm.bias": "pytorch_model-00002-of-00011.bin",
21
+ "language_model.model.layers.0.self_attn.k_layernorm.weight": "pytorch_model-00002-of-00011.bin",
22
+ "language_model.model.layers.0.self_attn.q_layernorm.bias": "pytorch_model-00002-of-00011.bin",
23
+ "language_model.model.layers.0.self_attn.q_layernorm.weight": "pytorch_model-00002-of-00011.bin",
24
+ "language_model.model.layers.0.self_attn.query_key_value.bias": "pytorch_model-00002-of-00011.bin",
25
+ "language_model.model.layers.0.self_attn.query_key_value.weight": "pytorch_model-00002-of-00011.bin",
26
+ "language_model.model.layers.1.input_layernorm.bias": "pytorch_model-00002-of-00011.bin",
27
+ "language_model.model.layers.1.input_layernorm.weight": "pytorch_model-00002-of-00011.bin",
28
+ "language_model.model.layers.1.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00011.bin",
29
+ "language_model.model.layers.1.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00011.bin",
30
+ "language_model.model.layers.1.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00011.bin",
31
+ "language_model.model.layers.1.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00011.bin",
32
+ "language_model.model.layers.1.post_attention_layernorm.bias": "pytorch_model-00002-of-00011.bin",
33
+ "language_model.model.layers.1.post_attention_layernorm.weight": "pytorch_model-00002-of-00011.bin",
34
+ "language_model.model.layers.1.self_attn.dense.bias": "pytorch_model-00002-of-00011.bin",
35
+ "language_model.model.layers.1.self_attn.dense.weight": "pytorch_model-00002-of-00011.bin",
36
+ "language_model.model.layers.1.self_attn.k_layernorm.bias": "pytorch_model-00002-of-00011.bin",
37
+ "language_model.model.layers.1.self_attn.k_layernorm.weight": "pytorch_model-00002-of-00011.bin",
38
+ "language_model.model.layers.1.self_attn.q_layernorm.bias": "pytorch_model-00002-of-00011.bin",
39
+ "language_model.model.layers.1.self_attn.q_layernorm.weight": "pytorch_model-00002-of-00011.bin",
40
+ "language_model.model.layers.1.self_attn.query_key_value.bias": "pytorch_model-00002-of-00011.bin",
41
+ "language_model.model.layers.1.self_attn.query_key_value.weight": "pytorch_model-00002-of-00011.bin",
42
+ "language_model.model.layers.10.input_layernorm.bias": "pytorch_model-00004-of-00011.bin",
43
+ "language_model.model.layers.10.input_layernorm.weight": "pytorch_model-00004-of-00011.bin",
44
+ "language_model.model.layers.10.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00011.bin",
45
+ "language_model.model.layers.10.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00011.bin",
46
+ "language_model.model.layers.10.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00011.bin",
47
+ "language_model.model.layers.10.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00011.bin",
48
+ "language_model.model.layers.10.post_attention_layernorm.bias": "pytorch_model-00004-of-00011.bin",
49
+ "language_model.model.layers.10.post_attention_layernorm.weight": "pytorch_model-00004-of-00011.bin",
50
+ "language_model.model.layers.10.self_attn.dense.bias": "pytorch_model-00004-of-00011.bin",
51
+ "language_model.model.layers.10.self_attn.dense.weight": "pytorch_model-00004-of-00011.bin",
52
+ "language_model.model.layers.10.self_attn.k_layernorm.bias": "pytorch_model-00004-of-00011.bin",
53
+ "language_model.model.layers.10.self_attn.k_layernorm.weight": "pytorch_model-00004-of-00011.bin",
54
+ "language_model.model.layers.10.self_attn.q_layernorm.bias": "pytorch_model-00004-of-00011.bin",
55
+ "language_model.model.layers.10.self_attn.q_layernorm.weight": "pytorch_model-00004-of-00011.bin",
56
+ "language_model.model.layers.10.self_attn.query_key_value.bias": "pytorch_model-00004-of-00011.bin",
57
+ "language_model.model.layers.10.self_attn.query_key_value.weight": "pytorch_model-00004-of-00011.bin",
58
+ "language_model.model.layers.11.input_layernorm.bias": "pytorch_model-00004-of-00011.bin",
59
+ "language_model.model.layers.11.input_layernorm.weight": "pytorch_model-00004-of-00011.bin",
60
+ "language_model.model.layers.11.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00011.bin",
61
+ "language_model.model.layers.11.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00011.bin",
62
+ "language_model.model.layers.11.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00011.bin",
63
+ "language_model.model.layers.11.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00011.bin",
64
+ "language_model.model.layers.11.post_attention_layernorm.bias": "pytorch_model-00004-of-00011.bin",
65
+ "language_model.model.layers.11.post_attention_layernorm.weight": "pytorch_model-00004-of-00011.bin",
66
+ "language_model.model.layers.11.self_attn.dense.bias": "pytorch_model-00004-of-00011.bin",
67
+ "language_model.model.layers.11.self_attn.dense.weight": "pytorch_model-00004-of-00011.bin",
68
+ "language_model.model.layers.11.self_attn.k_layernorm.bias": "pytorch_model-00004-of-00011.bin",
69
+ "language_model.model.layers.11.self_attn.k_layernorm.weight": "pytorch_model-00004-of-00011.bin",
70
+ "language_model.model.layers.11.self_attn.q_layernorm.bias": "pytorch_model-00004-of-00011.bin",
71
+ "language_model.model.layers.11.self_attn.q_layernorm.weight": "pytorch_model-00004-of-00011.bin",
72
+ "language_model.model.layers.11.self_attn.query_key_value.bias": "pytorch_model-00004-of-00011.bin",
73
+ "language_model.model.layers.11.self_attn.query_key_value.weight": "pytorch_model-00004-of-00011.bin",
74
+ "language_model.model.layers.12.input_layernorm.bias": "pytorch_model-00004-of-00011.bin",
75
+ "language_model.model.layers.12.input_layernorm.weight": "pytorch_model-00004-of-00011.bin",
76
+ "language_model.model.layers.12.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00011.bin",
77
+ "language_model.model.layers.12.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00011.bin",
78
+ "language_model.model.layers.12.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00011.bin",
79
+ "language_model.model.layers.12.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00011.bin",
80
+ "language_model.model.layers.12.post_attention_layernorm.bias": "pytorch_model-00004-of-00011.bin",
81
+ "language_model.model.layers.12.post_attention_layernorm.weight": "pytorch_model-00004-of-00011.bin",
82
+ "language_model.model.layers.12.self_attn.dense.bias": "pytorch_model-00004-of-00011.bin",
83
+ "language_model.model.layers.12.self_attn.dense.weight": "pytorch_model-00004-of-00011.bin",
84
+ "language_model.model.layers.12.self_attn.k_layernorm.bias": "pytorch_model-00004-of-00011.bin",
85
+ "language_model.model.layers.12.self_attn.k_layernorm.weight": "pytorch_model-00004-of-00011.bin",
86
+ "language_model.model.layers.12.self_attn.q_layernorm.bias": "pytorch_model-00004-of-00011.bin",
87
+ "language_model.model.layers.12.self_attn.q_layernorm.weight": "pytorch_model-00004-of-00011.bin",
88
+ "language_model.model.layers.12.self_attn.query_key_value.bias": "pytorch_model-00004-of-00011.bin",
89
+ "language_model.model.layers.12.self_attn.query_key_value.weight": "pytorch_model-00004-of-00011.bin",
90
+ "language_model.model.layers.13.input_layernorm.bias": "pytorch_model-00004-of-00011.bin",
91
+ "language_model.model.layers.13.input_layernorm.weight": "pytorch_model-00004-of-00011.bin",
92
+ "language_model.model.layers.13.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00011.bin",
93
+ "language_model.model.layers.13.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00011.bin",
94
+ "language_model.model.layers.13.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00011.bin",
95
+ "language_model.model.layers.13.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00011.bin",
96
+ "language_model.model.layers.13.post_attention_layernorm.bias": "pytorch_model-00004-of-00011.bin",
97
+ "language_model.model.layers.13.post_attention_layernorm.weight": "pytorch_model-00004-of-00011.bin",
98
+ "language_model.model.layers.13.self_attn.dense.bias": "pytorch_model-00004-of-00011.bin",
99
+ "language_model.model.layers.13.self_attn.dense.weight": "pytorch_model-00004-of-00011.bin",
100
+ "language_model.model.layers.13.self_attn.k_layernorm.bias": "pytorch_model-00004-of-00011.bin",
101
+ "language_model.model.layers.13.self_attn.k_layernorm.weight": "pytorch_model-00004-of-00011.bin",
102
+ "language_model.model.layers.13.self_attn.q_layernorm.bias": "pytorch_model-00004-of-00011.bin",
103
+ "language_model.model.layers.13.self_attn.q_layernorm.weight": "pytorch_model-00004-of-00011.bin",
104
+ "language_model.model.layers.13.self_attn.query_key_value.bias": "pytorch_model-00004-of-00011.bin",
105
+ "language_model.model.layers.13.self_attn.query_key_value.weight": "pytorch_model-00004-of-00011.bin",
106
+ "language_model.model.layers.14.input_layernorm.bias": "pytorch_model-00005-of-00011.bin",
107
+ "language_model.model.layers.14.input_layernorm.weight": "pytorch_model-00005-of-00011.bin",
108
+ "language_model.model.layers.14.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00011.bin",
109
+ "language_model.model.layers.14.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00011.bin",
110
+ "language_model.model.layers.14.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00011.bin",
111
+ "language_model.model.layers.14.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00011.bin",
112
+ "language_model.model.layers.14.post_attention_layernorm.bias": "pytorch_model-00005-of-00011.bin",
113
+ "language_model.model.layers.14.post_attention_layernorm.weight": "pytorch_model-00005-of-00011.bin",
114
+ "language_model.model.layers.14.self_attn.dense.bias": "pytorch_model-00005-of-00011.bin",
115
+ "language_model.model.layers.14.self_attn.dense.weight": "pytorch_model-00005-of-00011.bin",
116
+ "language_model.model.layers.14.self_attn.k_layernorm.bias": "pytorch_model-00005-of-00011.bin",
117
+ "language_model.model.layers.14.self_attn.k_layernorm.weight": "pytorch_model-00005-of-00011.bin",
118
+ "language_model.model.layers.14.self_attn.q_layernorm.bias": "pytorch_model-00005-of-00011.bin",
119
+ "language_model.model.layers.14.self_attn.q_layernorm.weight": "pytorch_model-00005-of-00011.bin",
120
+ "language_model.model.layers.14.self_attn.query_key_value.bias": "pytorch_model-00004-of-00011.bin",
121
+ "language_model.model.layers.14.self_attn.query_key_value.weight": "pytorch_model-00004-of-00011.bin",
122
+ "language_model.model.layers.15.input_layernorm.bias": "pytorch_model-00005-of-00011.bin",
123
+ "language_model.model.layers.15.input_layernorm.weight": "pytorch_model-00005-of-00011.bin",
124
+ "language_model.model.layers.15.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00011.bin",
125
+ "language_model.model.layers.15.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00011.bin",
126
+ "language_model.model.layers.15.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00011.bin",
127
+ "language_model.model.layers.15.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00011.bin",
128
+ "language_model.model.layers.15.post_attention_layernorm.bias": "pytorch_model-00005-of-00011.bin",
129
+ "language_model.model.layers.15.post_attention_layernorm.weight": "pytorch_model-00005-of-00011.bin",
130
+ "language_model.model.layers.15.self_attn.dense.bias": "pytorch_model-00005-of-00011.bin",
131
+ "language_model.model.layers.15.self_attn.dense.weight": "pytorch_model-00005-of-00011.bin",
132
+ "language_model.model.layers.15.self_attn.k_layernorm.bias": "pytorch_model-00005-of-00011.bin",
133
+ "language_model.model.layers.15.self_attn.k_layernorm.weight": "pytorch_model-00005-of-00011.bin",
134
+ "language_model.model.layers.15.self_attn.q_layernorm.bias": "pytorch_model-00005-of-00011.bin",
135
+ "language_model.model.layers.15.self_attn.q_layernorm.weight": "pytorch_model-00005-of-00011.bin",
136
+ "language_model.model.layers.15.self_attn.query_key_value.bias": "pytorch_model-00005-of-00011.bin",
137
+ "language_model.model.layers.15.self_attn.query_key_value.weight": "pytorch_model-00005-of-00011.bin",
138
+ "language_model.model.layers.16.input_layernorm.bias": "pytorch_model-00005-of-00011.bin",
139
+ "language_model.model.layers.16.input_layernorm.weight": "pytorch_model-00005-of-00011.bin",
140
+ "language_model.model.layers.16.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00011.bin",
141
+ "language_model.model.layers.16.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00011.bin",
142
+ "language_model.model.layers.16.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00011.bin",
143
+ "language_model.model.layers.16.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00011.bin",
144
+ "language_model.model.layers.16.post_attention_layernorm.bias": "pytorch_model-00005-of-00011.bin",
145
+ "language_model.model.layers.16.post_attention_layernorm.weight": "pytorch_model-00005-of-00011.bin",
146
+ "language_model.model.layers.16.self_attn.dense.bias": "pytorch_model-00005-of-00011.bin",
147
+ "language_model.model.layers.16.self_attn.dense.weight": "pytorch_model-00005-of-00011.bin",
148
+ "language_model.model.layers.16.self_attn.k_layernorm.bias": "pytorch_model-00005-of-00011.bin",
149
+ "language_model.model.layers.16.self_attn.k_layernorm.weight": "pytorch_model-00005-of-00011.bin",
150
+ "language_model.model.layers.16.self_attn.q_layernorm.bias": "pytorch_model-00005-of-00011.bin",
151
+ "language_model.model.layers.16.self_attn.q_layernorm.weight": "pytorch_model-00005-of-00011.bin",
152
+ "language_model.model.layers.16.self_attn.query_key_value.bias": "pytorch_model-00005-of-00011.bin",
153
+ "language_model.model.layers.16.self_attn.query_key_value.weight": "pytorch_model-00005-of-00011.bin",
154
+ "language_model.model.layers.17.input_layernorm.bias": "pytorch_model-00005-of-00011.bin",
155
+ "language_model.model.layers.17.input_layernorm.weight": "pytorch_model-00005-of-00011.bin",
156
+ "language_model.model.layers.17.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00011.bin",
157
+ "language_model.model.layers.17.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00011.bin",
158
+ "language_model.model.layers.17.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00011.bin",
159
+ "language_model.model.layers.17.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00011.bin",
160
+ "language_model.model.layers.17.post_attention_layernorm.bias": "pytorch_model-00005-of-00011.bin",
161
+ "language_model.model.layers.17.post_attention_layernorm.weight": "pytorch_model-00005-of-00011.bin",
162
+ "language_model.model.layers.17.self_attn.dense.bias": "pytorch_model-00005-of-00011.bin",
163
+ "language_model.model.layers.17.self_attn.dense.weight": "pytorch_model-00005-of-00011.bin",
164
+ "language_model.model.layers.17.self_attn.k_layernorm.bias": "pytorch_model-00005-of-00011.bin",
165
+ "language_model.model.layers.17.self_attn.k_layernorm.weight": "pytorch_model-00005-of-00011.bin",
166
+ "language_model.model.layers.17.self_attn.q_layernorm.bias": "pytorch_model-00005-of-00011.bin",
167
+ "language_model.model.layers.17.self_attn.q_layernorm.weight": "pytorch_model-00005-of-00011.bin",
168
+ "language_model.model.layers.17.self_attn.query_key_value.bias": "pytorch_model-00005-of-00011.bin",
169
+ "language_model.model.layers.17.self_attn.query_key_value.weight": "pytorch_model-00005-of-00011.bin",
170
+ "language_model.model.layers.18.input_layernorm.bias": "pytorch_model-00005-of-00011.bin",
171
+ "language_model.model.layers.18.input_layernorm.weight": "pytorch_model-00005-of-00011.bin",
172
+ "language_model.model.layers.18.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00011.bin",
173
+ "language_model.model.layers.18.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00011.bin",
174
+ "language_model.model.layers.18.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00011.bin",
175
+ "language_model.model.layers.18.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00011.bin",
176
+ "language_model.model.layers.18.post_attention_layernorm.bias": "pytorch_model-00005-of-00011.bin",
177
+ "language_model.model.layers.18.post_attention_layernorm.weight": "pytorch_model-00005-of-00011.bin",
178
+ "language_model.model.layers.18.self_attn.dense.bias": "pytorch_model-00005-of-00011.bin",
179
+ "language_model.model.layers.18.self_attn.dense.weight": "pytorch_model-00005-of-00011.bin",
180
+ "language_model.model.layers.18.self_attn.k_layernorm.bias": "pytorch_model-00005-of-00011.bin",
181
+ "language_model.model.layers.18.self_attn.k_layernorm.weight": "pytorch_model-00005-of-00011.bin",
182
+ "language_model.model.layers.18.self_attn.q_layernorm.bias": "pytorch_model-00005-of-00011.bin",
183
+ "language_model.model.layers.18.self_attn.q_layernorm.weight": "pytorch_model-00005-of-00011.bin",
184
+ "language_model.model.layers.18.self_attn.query_key_value.bias": "pytorch_model-00005-of-00011.bin",
185
+ "language_model.model.layers.18.self_attn.query_key_value.weight": "pytorch_model-00005-of-00011.bin",
186
+ "language_model.model.layers.19.input_layernorm.bias": "pytorch_model-00006-of-00011.bin",
187
+ "language_model.model.layers.19.input_layernorm.weight": "pytorch_model-00006-of-00011.bin",
188
+ "language_model.model.layers.19.mlp.dense_4h_to_h.bias": "pytorch_model-00006-of-00011.bin",
189
+ "language_model.model.layers.19.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00011.bin",
190
+ "language_model.model.layers.19.mlp.dense_h_to_4h.bias": "pytorch_model-00006-of-00011.bin",
191
+ "language_model.model.layers.19.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00011.bin",
192
+ "language_model.model.layers.19.post_attention_layernorm.bias": "pytorch_model-00006-of-00011.bin",
193
+ "language_model.model.layers.19.post_attention_layernorm.weight": "pytorch_model-00006-of-00011.bin",
194
+ "language_model.model.layers.19.self_attn.dense.bias": "pytorch_model-00006-of-00011.bin",
195
+ "language_model.model.layers.19.self_attn.dense.weight": "pytorch_model-00006-of-00011.bin",
196
+ "language_model.model.layers.19.self_attn.k_layernorm.bias": "pytorch_model-00006-of-00011.bin",
197
+ "language_model.model.layers.19.self_attn.k_layernorm.weight": "pytorch_model-00006-of-00011.bin",
198
+ "language_model.model.layers.19.self_attn.q_layernorm.bias": "pytorch_model-00006-of-00011.bin",
199
+ "language_model.model.layers.19.self_attn.q_layernorm.weight": "pytorch_model-00006-of-00011.bin",
200
+ "language_model.model.layers.19.self_attn.query_key_value.bias": "pytorch_model-00006-of-00011.bin",
201
+ "language_model.model.layers.19.self_attn.query_key_value.weight": "pytorch_model-00006-of-00011.bin",
202
+ "language_model.model.layers.2.input_layernorm.bias": "pytorch_model-00002-of-00011.bin",
203
+ "language_model.model.layers.2.input_layernorm.weight": "pytorch_model-00002-of-00011.bin",
204
+ "language_model.model.layers.2.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00011.bin",
205
+ "language_model.model.layers.2.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00011.bin",
206
+ "language_model.model.layers.2.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00011.bin",
207
+ "language_model.model.layers.2.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00011.bin",
208
+ "language_model.model.layers.2.post_attention_layernorm.bias": "pytorch_model-00002-of-00011.bin",
209
+ "language_model.model.layers.2.post_attention_layernorm.weight": "pytorch_model-00002-of-00011.bin",
210
+ "language_model.model.layers.2.self_attn.dense.bias": "pytorch_model-00002-of-00011.bin",
211
+ "language_model.model.layers.2.self_attn.dense.weight": "pytorch_model-00002-of-00011.bin",
212
+ "language_model.model.layers.2.self_attn.k_layernorm.bias": "pytorch_model-00002-of-00011.bin",
213
+ "language_model.model.layers.2.self_attn.k_layernorm.weight": "pytorch_model-00002-of-00011.bin",
214
+ "language_model.model.layers.2.self_attn.q_layernorm.bias": "pytorch_model-00002-of-00011.bin",
215
+ "language_model.model.layers.2.self_attn.q_layernorm.weight": "pytorch_model-00002-of-00011.bin",
216
+ "language_model.model.layers.2.self_attn.query_key_value.bias": "pytorch_model-00002-of-00011.bin",
217
+ "language_model.model.layers.2.self_attn.query_key_value.weight": "pytorch_model-00002-of-00011.bin",
218
+ "language_model.model.layers.20.input_layernorm.bias": "pytorch_model-00006-of-00011.bin",
219
+ "language_model.model.layers.20.input_layernorm.weight": "pytorch_model-00006-of-00011.bin",
220
+ "language_model.model.layers.20.mlp.dense_4h_to_h.bias": "pytorch_model-00006-of-00011.bin",
221
+ "language_model.model.layers.20.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00011.bin",
222
+ "language_model.model.layers.20.mlp.dense_h_to_4h.bias": "pytorch_model-00006-of-00011.bin",
223
+ "language_model.model.layers.20.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00011.bin",
224
+ "language_model.model.layers.20.post_attention_layernorm.bias": "pytorch_model-00006-of-00011.bin",
225
+ "language_model.model.layers.20.post_attention_layernorm.weight": "pytorch_model-00006-of-00011.bin",
226
+ "language_model.model.layers.20.self_attn.dense.bias": "pytorch_model-00006-of-00011.bin",
227
+ "language_model.model.layers.20.self_attn.dense.weight": "pytorch_model-00006-of-00011.bin",
228
+ "language_model.model.layers.20.self_attn.k_layernorm.bias": "pytorch_model-00006-of-00011.bin",
229
+ "language_model.model.layers.20.self_attn.k_layernorm.weight": "pytorch_model-00006-of-00011.bin",
230
+ "language_model.model.layers.20.self_attn.q_layernorm.bias": "pytorch_model-00006-of-00011.bin",
231
+ "language_model.model.layers.20.self_attn.q_layernorm.weight": "pytorch_model-00006-of-00011.bin",
232
+ "language_model.model.layers.20.self_attn.query_key_value.bias": "pytorch_model-00006-of-00011.bin",
233
+ "language_model.model.layers.20.self_attn.query_key_value.weight": "pytorch_model-00006-of-00011.bin",
234
+ "language_model.model.layers.21.input_layernorm.bias": "pytorch_model-00006-of-00011.bin",
235
+ "language_model.model.layers.21.input_layernorm.weight": "pytorch_model-00006-of-00011.bin",
236
+ "language_model.model.layers.21.mlp.dense_4h_to_h.bias": "pytorch_model-00006-of-00011.bin",
237
+ "language_model.model.layers.21.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00011.bin",
238
+ "language_model.model.layers.21.mlp.dense_h_to_4h.bias": "pytorch_model-00006-of-00011.bin",
239
+ "language_model.model.layers.21.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00011.bin",
240
+ "language_model.model.layers.21.post_attention_layernorm.bias": "pytorch_model-00006-of-00011.bin",
241
+ "language_model.model.layers.21.post_attention_layernorm.weight": "pytorch_model-00006-of-00011.bin",
242
+ "language_model.model.layers.21.self_attn.dense.bias": "pytorch_model-00006-of-00011.bin",
243
+ "language_model.model.layers.21.self_attn.dense.weight": "pytorch_model-00006-of-00011.bin",
244
+ "language_model.model.layers.21.self_attn.k_layernorm.bias": "pytorch_model-00006-of-00011.bin",
245
+ "language_model.model.layers.21.self_attn.k_layernorm.weight": "pytorch_model-00006-of-00011.bin",
246
+ "language_model.model.layers.21.self_attn.q_layernorm.bias": "pytorch_model-00006-of-00011.bin",
247
+ "language_model.model.layers.21.self_attn.q_layernorm.weight": "pytorch_model-00006-of-00011.bin",
248
+ "language_model.model.layers.21.self_attn.query_key_value.bias": "pytorch_model-00006-of-00011.bin",
249
+ "language_model.model.layers.21.self_attn.query_key_value.weight": "pytorch_model-00006-of-00011.bin",
250
+ "language_model.model.layers.22.input_layernorm.bias": "pytorch_model-00006-of-00011.bin",
251
+ "language_model.model.layers.22.input_layernorm.weight": "pytorch_model-00006-of-00011.bin",
252
+ "language_model.model.layers.22.mlp.dense_4h_to_h.bias": "pytorch_model-00006-of-00011.bin",
253
+ "language_model.model.layers.22.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00011.bin",
254
+ "language_model.model.layers.22.mlp.dense_h_to_4h.bias": "pytorch_model-00006-of-00011.bin",
255
+ "language_model.model.layers.22.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00011.bin",
256
+ "language_model.model.layers.22.post_attention_layernorm.bias": "pytorch_model-00006-of-00011.bin",
257
+ "language_model.model.layers.22.post_attention_layernorm.weight": "pytorch_model-00006-of-00011.bin",
258
+ "language_model.model.layers.22.self_attn.dense.bias": "pytorch_model-00006-of-00011.bin",
259
+ "language_model.model.layers.22.self_attn.dense.weight": "pytorch_model-00006-of-00011.bin",
260
+ "language_model.model.layers.22.self_attn.k_layernorm.bias": "pytorch_model-00006-of-00011.bin",
261
+ "language_model.model.layers.22.self_attn.k_layernorm.weight": "pytorch_model-00006-of-00011.bin",
262
+ "language_model.model.layers.22.self_attn.q_layernorm.bias": "pytorch_model-00006-of-00011.bin",
263
+ "language_model.model.layers.22.self_attn.q_layernorm.weight": "pytorch_model-00006-of-00011.bin",
264
+ "language_model.model.layers.22.self_attn.query_key_value.bias": "pytorch_model-00006-of-00011.bin",
265
+ "language_model.model.layers.22.self_attn.query_key_value.weight": "pytorch_model-00006-of-00011.bin",
266
+ "language_model.model.layers.23.input_layernorm.bias": "pytorch_model-00007-of-00011.bin",
267
+ "language_model.model.layers.23.input_layernorm.weight": "pytorch_model-00007-of-00011.bin",
268
+ "language_model.model.layers.23.mlp.dense_4h_to_h.bias": "pytorch_model-00007-of-00011.bin",
269
+ "language_model.model.layers.23.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00011.bin",
270
+ "language_model.model.layers.23.mlp.dense_h_to_4h.bias": "pytorch_model-00006-of-00011.bin",
271
+ "language_model.model.layers.23.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00011.bin",
272
+ "language_model.model.layers.23.post_attention_layernorm.bias": "pytorch_model-00007-of-00011.bin",
273
+ "language_model.model.layers.23.post_attention_layernorm.weight": "pytorch_model-00007-of-00011.bin",
274
+ "language_model.model.layers.23.self_attn.dense.bias": "pytorch_model-00006-of-00011.bin",
275
+ "language_model.model.layers.23.self_attn.dense.weight": "pytorch_model-00006-of-00011.bin",
276
+ "language_model.model.layers.23.self_attn.k_layernorm.bias": "pytorch_model-00006-of-00011.bin",
277
+ "language_model.model.layers.23.self_attn.k_layernorm.weight": "pytorch_model-00006-of-00011.bin",
278
+ "language_model.model.layers.23.self_attn.q_layernorm.bias": "pytorch_model-00006-of-00011.bin",
279
+ "language_model.model.layers.23.self_attn.q_layernorm.weight": "pytorch_model-00006-of-00011.bin",
280
+ "language_model.model.layers.23.self_attn.query_key_value.bias": "pytorch_model-00006-of-00011.bin",
281
+ "language_model.model.layers.23.self_attn.query_key_value.weight": "pytorch_model-00006-of-00011.bin",
282
+ "language_model.model.layers.24.input_layernorm.bias": "pytorch_model-00007-of-00011.bin",
283
+ "language_model.model.layers.24.input_layernorm.weight": "pytorch_model-00007-of-00011.bin",
284
+ "language_model.model.layers.24.mlp.dense_4h_to_h.bias": "pytorch_model-00007-of-00011.bin",
285
+ "language_model.model.layers.24.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00011.bin",
286
+ "language_model.model.layers.24.mlp.dense_h_to_4h.bias": "pytorch_model-00007-of-00011.bin",
287
+ "language_model.model.layers.24.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00011.bin",
288
+ "language_model.model.layers.24.post_attention_layernorm.bias": "pytorch_model-00007-of-00011.bin",
289
+ "language_model.model.layers.24.post_attention_layernorm.weight": "pytorch_model-00007-of-00011.bin",
290
+ "language_model.model.layers.24.self_attn.dense.bias": "pytorch_model-00007-of-00011.bin",
291
+ "language_model.model.layers.24.self_attn.dense.weight": "pytorch_model-00007-of-00011.bin",
292
+ "language_model.model.layers.24.self_attn.k_layernorm.bias": "pytorch_model-00007-of-00011.bin",
293
+ "language_model.model.layers.24.self_attn.k_layernorm.weight": "pytorch_model-00007-of-00011.bin",
294
+ "language_model.model.layers.24.self_attn.q_layernorm.bias": "pytorch_model-00007-of-00011.bin",
295
+ "language_model.model.layers.24.self_attn.q_layernorm.weight": "pytorch_model-00007-of-00011.bin",
296
+ "language_model.model.layers.24.self_attn.query_key_value.bias": "pytorch_model-00007-of-00011.bin",
297
+ "language_model.model.layers.24.self_attn.query_key_value.weight": "pytorch_model-00007-of-00011.bin",
298
+ "language_model.model.layers.25.input_layernorm.bias": "pytorch_model-00007-of-00011.bin",
299
+ "language_model.model.layers.25.input_layernorm.weight": "pytorch_model-00007-of-00011.bin",
300
+ "language_model.model.layers.25.mlp.dense_4h_to_h.bias": "pytorch_model-00007-of-00011.bin",
301
+ "language_model.model.layers.25.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00011.bin",
302
+ "language_model.model.layers.25.mlp.dense_h_to_4h.bias": "pytorch_model-00007-of-00011.bin",
303
+ "language_model.model.layers.25.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00011.bin",
304
+ "language_model.model.layers.25.post_attention_layernorm.bias": "pytorch_model-00007-of-00011.bin",
305
+ "language_model.model.layers.25.post_attention_layernorm.weight": "pytorch_model-00007-of-00011.bin",
306
+ "language_model.model.layers.25.self_attn.dense.bias": "pytorch_model-00007-of-00011.bin",
307
+ "language_model.model.layers.25.self_attn.dense.weight": "pytorch_model-00007-of-00011.bin",
308
+ "language_model.model.layers.25.self_attn.k_layernorm.bias": "pytorch_model-00007-of-00011.bin",
309
+ "language_model.model.layers.25.self_attn.k_layernorm.weight": "pytorch_model-00007-of-00011.bin",
310
+ "language_model.model.layers.25.self_attn.q_layernorm.bias": "pytorch_model-00007-of-00011.bin",
311
+ "language_model.model.layers.25.self_attn.q_layernorm.weight": "pytorch_model-00007-of-00011.bin",
312
+ "language_model.model.layers.25.self_attn.query_key_value.bias": "pytorch_model-00007-of-00011.bin",
313
+ "language_model.model.layers.25.self_attn.query_key_value.weight": "pytorch_model-00007-of-00011.bin",
314
+ "language_model.model.layers.26.input_layernorm.bias": "pytorch_model-00007-of-00011.bin",
315
+ "language_model.model.layers.26.input_layernorm.weight": "pytorch_model-00007-of-00011.bin",
316
+ "language_model.model.layers.26.mlp.dense_4h_to_h.bias": "pytorch_model-00007-of-00011.bin",
317
+ "language_model.model.layers.26.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00011.bin",
318
+ "language_model.model.layers.26.mlp.dense_h_to_4h.bias": "pytorch_model-00007-of-00011.bin",
319
+ "language_model.model.layers.26.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00011.bin",
320
+ "language_model.model.layers.26.post_attention_layernorm.bias": "pytorch_model-00007-of-00011.bin",
321
+ "language_model.model.layers.26.post_attention_layernorm.weight": "pytorch_model-00007-of-00011.bin",
322
+ "language_model.model.layers.26.self_attn.dense.bias": "pytorch_model-00007-of-00011.bin",
323
+ "language_model.model.layers.26.self_attn.dense.weight": "pytorch_model-00007-of-00011.bin",
324
+ "language_model.model.layers.26.self_attn.k_layernorm.bias": "pytorch_model-00007-of-00011.bin",
325
+ "language_model.model.layers.26.self_attn.k_layernorm.weight": "pytorch_model-00007-of-00011.bin",
326
+ "language_model.model.layers.26.self_attn.q_layernorm.bias": "pytorch_model-00007-of-00011.bin",
327
+ "language_model.model.layers.26.self_attn.q_layernorm.weight": "pytorch_model-00007-of-00011.bin",
328
+ "language_model.model.layers.26.self_attn.query_key_value.bias": "pytorch_model-00007-of-00011.bin",
329
+ "language_model.model.layers.26.self_attn.query_key_value.weight": "pytorch_model-00007-of-00011.bin",
330
+ "language_model.model.layers.27.input_layernorm.bias": "pytorch_model-00007-of-00011.bin",
331
+ "language_model.model.layers.27.input_layernorm.weight": "pytorch_model-00007-of-00011.bin",
332
+ "language_model.model.layers.27.mlp.dense_4h_to_h.bias": "pytorch_model-00007-of-00011.bin",
333
+ "language_model.model.layers.27.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00011.bin",
334
+ "language_model.model.layers.27.mlp.dense_h_to_4h.bias": "pytorch_model-00007-of-00011.bin",
335
+ "language_model.model.layers.27.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00011.bin",
336
+ "language_model.model.layers.27.post_attention_layernorm.bias": "pytorch_model-00007-of-00011.bin",
337
+ "language_model.model.layers.27.post_attention_layernorm.weight": "pytorch_model-00007-of-00011.bin",
338
+ "language_model.model.layers.27.self_attn.dense.bias": "pytorch_model-00007-of-00011.bin",
339
+ "language_model.model.layers.27.self_attn.dense.weight": "pytorch_model-00007-of-00011.bin",
340
+ "language_model.model.layers.27.self_attn.k_layernorm.bias": "pytorch_model-00007-of-00011.bin",
341
+ "language_model.model.layers.27.self_attn.k_layernorm.weight": "pytorch_model-00007-of-00011.bin",
342
+ "language_model.model.layers.27.self_attn.q_layernorm.bias": "pytorch_model-00007-of-00011.bin",
343
+ "language_model.model.layers.27.self_attn.q_layernorm.weight": "pytorch_model-00007-of-00011.bin",
344
+ "language_model.model.layers.27.self_attn.query_key_value.bias": "pytorch_model-00007-of-00011.bin",
345
+ "language_model.model.layers.27.self_attn.query_key_value.weight": "pytorch_model-00007-of-00011.bin",
346
+ "language_model.model.layers.28.input_layernorm.bias": "pytorch_model-00008-of-00011.bin",
347
+ "language_model.model.layers.28.input_layernorm.weight": "pytorch_model-00008-of-00011.bin",
348
+ "language_model.model.layers.28.mlp.dense_4h_to_h.bias": "pytorch_model-00008-of-00011.bin",
349
+ "language_model.model.layers.28.mlp.dense_4h_to_h.weight": "pytorch_model-00008-of-00011.bin",
350
+ "language_model.model.layers.28.mlp.dense_h_to_4h.bias": "pytorch_model-00008-of-00011.bin",
351
+ "language_model.model.layers.28.mlp.dense_h_to_4h.weight": "pytorch_model-00008-of-00011.bin",
352
+ "language_model.model.layers.28.post_attention_layernorm.bias": "pytorch_model-00008-of-00011.bin",
353
+ "language_model.model.layers.28.post_attention_layernorm.weight": "pytorch_model-00008-of-00011.bin",
354
+ "language_model.model.layers.28.self_attn.dense.bias": "pytorch_model-00007-of-00011.bin",
355
+ "language_model.model.layers.28.self_attn.dense.weight": "pytorch_model-00007-of-00011.bin",
356
+ "language_model.model.layers.28.self_attn.k_layernorm.bias": "pytorch_model-00007-of-00011.bin",
357
+ "language_model.model.layers.28.self_attn.k_layernorm.weight": "pytorch_model-00007-of-00011.bin",
358
+ "language_model.model.layers.28.self_attn.q_layernorm.bias": "pytorch_model-00007-of-00011.bin",
359
+ "language_model.model.layers.28.self_attn.q_layernorm.weight": "pytorch_model-00007-of-00011.bin",
360
+ "language_model.model.layers.28.self_attn.query_key_value.bias": "pytorch_model-00007-of-00011.bin",
361
+ "language_model.model.layers.28.self_attn.query_key_value.weight": "pytorch_model-00007-of-00011.bin",
362
+ "language_model.model.layers.29.input_layernorm.bias": "pytorch_model-00008-of-00011.bin",
363
+ "language_model.model.layers.29.input_layernorm.weight": "pytorch_model-00008-of-00011.bin",
364
+ "language_model.model.layers.29.mlp.dense_4h_to_h.bias": "pytorch_model-00008-of-00011.bin",
365
+ "language_model.model.layers.29.mlp.dense_4h_to_h.weight": "pytorch_model-00008-of-00011.bin",
366
+ "language_model.model.layers.29.mlp.dense_h_to_4h.bias": "pytorch_model-00008-of-00011.bin",
367
+ "language_model.model.layers.29.mlp.dense_h_to_4h.weight": "pytorch_model-00008-of-00011.bin",
368
+ "language_model.model.layers.29.post_attention_layernorm.bias": "pytorch_model-00008-of-00011.bin",
369
+ "language_model.model.layers.29.post_attention_layernorm.weight": "pytorch_model-00008-of-00011.bin",
370
+ "language_model.model.layers.29.self_attn.dense.bias": "pytorch_model-00008-of-00011.bin",
371
+ "language_model.model.layers.29.self_attn.dense.weight": "pytorch_model-00008-of-00011.bin",
372
+ "language_model.model.layers.29.self_attn.k_layernorm.bias": "pytorch_model-00008-of-00011.bin",
373
+ "language_model.model.layers.29.self_attn.k_layernorm.weight": "pytorch_model-00008-of-00011.bin",
374
+ "language_model.model.layers.29.self_attn.q_layernorm.bias": "pytorch_model-00008-of-00011.bin",
375
+ "language_model.model.layers.29.self_attn.q_layernorm.weight": "pytorch_model-00008-of-00011.bin",
376
+ "language_model.model.layers.29.self_attn.query_key_value.bias": "pytorch_model-00008-of-00011.bin",
377
+ "language_model.model.layers.29.self_attn.query_key_value.weight": "pytorch_model-00008-of-00011.bin",
378
+ "language_model.model.layers.3.input_layernorm.bias": "pytorch_model-00002-of-00011.bin",
379
+ "language_model.model.layers.3.input_layernorm.weight": "pytorch_model-00002-of-00011.bin",
380
+ "language_model.model.layers.3.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00011.bin",
381
+ "language_model.model.layers.3.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00011.bin",
382
+ "language_model.model.layers.3.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00011.bin",
383
+ "language_model.model.layers.3.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00011.bin",
384
+ "language_model.model.layers.3.post_attention_layernorm.bias": "pytorch_model-00002-of-00011.bin",
385
+ "language_model.model.layers.3.post_attention_layernorm.weight": "pytorch_model-00002-of-00011.bin",
386
+ "language_model.model.layers.3.self_attn.dense.bias": "pytorch_model-00002-of-00011.bin",
387
+ "language_model.model.layers.3.self_attn.dense.weight": "pytorch_model-00002-of-00011.bin",
388
+ "language_model.model.layers.3.self_attn.k_layernorm.bias": "pytorch_model-00002-of-00011.bin",
389
+ "language_model.model.layers.3.self_attn.k_layernorm.weight": "pytorch_model-00002-of-00011.bin",
390
+ "language_model.model.layers.3.self_attn.q_layernorm.bias": "pytorch_model-00002-of-00011.bin",
391
+ "language_model.model.layers.3.self_attn.q_layernorm.weight": "pytorch_model-00002-of-00011.bin",
392
+ "language_model.model.layers.3.self_attn.query_key_value.bias": "pytorch_model-00002-of-00011.bin",
393
+ "language_model.model.layers.3.self_attn.query_key_value.weight": "pytorch_model-00002-of-00011.bin",
394
+ "language_model.model.layers.30.input_layernorm.bias": "pytorch_model-00008-of-00011.bin",
395
+ "language_model.model.layers.30.input_layernorm.weight": "pytorch_model-00008-of-00011.bin",
396
+ "language_model.model.layers.30.mlp.dense_4h_to_h.bias": "pytorch_model-00008-of-00011.bin",
397
+ "language_model.model.layers.30.mlp.dense_4h_to_h.weight": "pytorch_model-00008-of-00011.bin",
398
+ "language_model.model.layers.30.mlp.dense_h_to_4h.bias": "pytorch_model-00008-of-00011.bin",
399
+ "language_model.model.layers.30.mlp.dense_h_to_4h.weight": "pytorch_model-00008-of-00011.bin",
400
+ "language_model.model.layers.30.post_attention_layernorm.bias": "pytorch_model-00008-of-00011.bin",
401
+ "language_model.model.layers.30.post_attention_layernorm.weight": "pytorch_model-00008-of-00011.bin",
402
+ "language_model.model.layers.30.self_attn.dense.bias": "pytorch_model-00008-of-00011.bin",
403
+ "language_model.model.layers.30.self_attn.dense.weight": "pytorch_model-00008-of-00011.bin",
404
+ "language_model.model.layers.30.self_attn.k_layernorm.bias": "pytorch_model-00008-of-00011.bin",
405
+ "language_model.model.layers.30.self_attn.k_layernorm.weight": "pytorch_model-00008-of-00011.bin",
406
+ "language_model.model.layers.30.self_attn.q_layernorm.bias": "pytorch_model-00008-of-00011.bin",
407
+ "language_model.model.layers.30.self_attn.q_layernorm.weight": "pytorch_model-00008-of-00011.bin",
408
+ "language_model.model.layers.30.self_attn.query_key_value.bias": "pytorch_model-00008-of-00011.bin",
409
+ "language_model.model.layers.30.self_attn.query_key_value.weight": "pytorch_model-00008-of-00011.bin",
410
+ "language_model.model.layers.31.input_layernorm.bias": "pytorch_model-00008-of-00011.bin",
411
+ "language_model.model.layers.31.input_layernorm.weight": "pytorch_model-00008-of-00011.bin",
412
+ "language_model.model.layers.31.mlp.dense_4h_to_h.bias": "pytorch_model-00008-of-00011.bin",
413
+ "language_model.model.layers.31.mlp.dense_4h_to_h.weight": "pytorch_model-00008-of-00011.bin",
414
+ "language_model.model.layers.31.mlp.dense_h_to_4h.bias": "pytorch_model-00008-of-00011.bin",
415
+ "language_model.model.layers.31.mlp.dense_h_to_4h.weight": "pytorch_model-00008-of-00011.bin",
416
+ "language_model.model.layers.31.post_attention_layernorm.bias": "pytorch_model-00008-of-00011.bin",
417
+ "language_model.model.layers.31.post_attention_layernorm.weight": "pytorch_model-00008-of-00011.bin",
418
+ "language_model.model.layers.31.self_attn.dense.bias": "pytorch_model-00008-of-00011.bin",
419
+ "language_model.model.layers.31.self_attn.dense.weight": "pytorch_model-00008-of-00011.bin",
420
+ "language_model.model.layers.31.self_attn.k_layernorm.bias": "pytorch_model-00008-of-00011.bin",
421
+ "language_model.model.layers.31.self_attn.k_layernorm.weight": "pytorch_model-00008-of-00011.bin",
422
+ "language_model.model.layers.31.self_attn.q_layernorm.bias": "pytorch_model-00008-of-00011.bin",
423
+ "language_model.model.layers.31.self_attn.q_layernorm.weight": "pytorch_model-00008-of-00011.bin",
424
+ "language_model.model.layers.31.self_attn.query_key_value.bias": "pytorch_model-00008-of-00011.bin",
425
+ "language_model.model.layers.31.self_attn.query_key_value.weight": "pytorch_model-00008-of-00011.bin",
426
+ "language_model.model.layers.32.input_layernorm.bias": "pytorch_model-00008-of-00011.bin",
427
+ "language_model.model.layers.32.input_layernorm.weight": "pytorch_model-00008-of-00011.bin",
428
+ "language_model.model.layers.32.mlp.dense_4h_to_h.bias": "pytorch_model-00008-of-00011.bin",
429
+ "language_model.model.layers.32.mlp.dense_4h_to_h.weight": "pytorch_model-00008-of-00011.bin",
430
+ "language_model.model.layers.32.mlp.dense_h_to_4h.bias": "pytorch_model-00008-of-00011.bin",
431
+ "language_model.model.layers.32.mlp.dense_h_to_4h.weight": "pytorch_model-00008-of-00011.bin",
432
+ "language_model.model.layers.32.post_attention_layernorm.bias": "pytorch_model-00008-of-00011.bin",
433
+ "language_model.model.layers.32.post_attention_layernorm.weight": "pytorch_model-00008-of-00011.bin",
434
+ "language_model.model.layers.32.self_attn.dense.bias": "pytorch_model-00008-of-00011.bin",
435
+ "language_model.model.layers.32.self_attn.dense.weight": "pytorch_model-00008-of-00011.bin",
436
+ "language_model.model.layers.32.self_attn.k_layernorm.bias": "pytorch_model-00008-of-00011.bin",
437
+ "language_model.model.layers.32.self_attn.k_layernorm.weight": "pytorch_model-00008-of-00011.bin",
438
+ "language_model.model.layers.32.self_attn.q_layernorm.bias": "pytorch_model-00008-of-00011.bin",
439
+ "language_model.model.layers.32.self_attn.q_layernorm.weight": "pytorch_model-00008-of-00011.bin",
440
+ "language_model.model.layers.32.self_attn.query_key_value.bias": "pytorch_model-00008-of-00011.bin",
441
+ "language_model.model.layers.32.self_attn.query_key_value.weight": "pytorch_model-00008-of-00011.bin",
442
+ "language_model.model.layers.33.input_layernorm.bias": "pytorch_model-00009-of-00011.bin",
443
+ "language_model.model.layers.33.input_layernorm.weight": "pytorch_model-00009-of-00011.bin",
444
+ "language_model.model.layers.33.mlp.dense_4h_to_h.bias": "pytorch_model-00009-of-00011.bin",
445
+ "language_model.model.layers.33.mlp.dense_4h_to_h.weight": "pytorch_model-00009-of-00011.bin",
446
+ "language_model.model.layers.33.mlp.dense_h_to_4h.bias": "pytorch_model-00009-of-00011.bin",
447
+ "language_model.model.layers.33.mlp.dense_h_to_4h.weight": "pytorch_model-00009-of-00011.bin",
448
+ "language_model.model.layers.33.post_attention_layernorm.bias": "pytorch_model-00009-of-00011.bin",
449
+ "language_model.model.layers.33.post_attention_layernorm.weight": "pytorch_model-00009-of-00011.bin",
450
+ "language_model.model.layers.33.self_attn.dense.bias": "pytorch_model-00009-of-00011.bin",
451
+ "language_model.model.layers.33.self_attn.dense.weight": "pytorch_model-00009-of-00011.bin",
452
+ "language_model.model.layers.33.self_attn.k_layernorm.bias": "pytorch_model-00009-of-00011.bin",
453
+ "language_model.model.layers.33.self_attn.k_layernorm.weight": "pytorch_model-00009-of-00011.bin",
454
+ "language_model.model.layers.33.self_attn.q_layernorm.bias": "pytorch_model-00009-of-00011.bin",
455
+ "language_model.model.layers.33.self_attn.q_layernorm.weight": "pytorch_model-00009-of-00011.bin",
456
+ "language_model.model.layers.33.self_attn.query_key_value.bias": "pytorch_model-00008-of-00011.bin",
457
+ "language_model.model.layers.33.self_attn.query_key_value.weight": "pytorch_model-00008-of-00011.bin",
458
+ "language_model.model.layers.34.input_layernorm.bias": "pytorch_model-00009-of-00011.bin",
459
+ "language_model.model.layers.34.input_layernorm.weight": "pytorch_model-00009-of-00011.bin",
460
+ "language_model.model.layers.34.mlp.dense_4h_to_h.bias": "pytorch_model-00009-of-00011.bin",
461
+ "language_model.model.layers.34.mlp.dense_4h_to_h.weight": "pytorch_model-00009-of-00011.bin",
462
+ "language_model.model.layers.34.mlp.dense_h_to_4h.bias": "pytorch_model-00009-of-00011.bin",
463
+ "language_model.model.layers.34.mlp.dense_h_to_4h.weight": "pytorch_model-00009-of-00011.bin",
464
+ "language_model.model.layers.34.post_attention_layernorm.bias": "pytorch_model-00009-of-00011.bin",
465
+ "language_model.model.layers.34.post_attention_layernorm.weight": "pytorch_model-00009-of-00011.bin",
466
+ "language_model.model.layers.34.self_attn.dense.bias": "pytorch_model-00009-of-00011.bin",
467
+ "language_model.model.layers.34.self_attn.dense.weight": "pytorch_model-00009-of-00011.bin",
468
+ "language_model.model.layers.34.self_attn.k_layernorm.bias": "pytorch_model-00009-of-00011.bin",
469
+ "language_model.model.layers.34.self_attn.k_layernorm.weight": "pytorch_model-00009-of-00011.bin",
470
+ "language_model.model.layers.34.self_attn.q_layernorm.bias": "pytorch_model-00009-of-00011.bin",
471
+ "language_model.model.layers.34.self_attn.q_layernorm.weight": "pytorch_model-00009-of-00011.bin",
472
+ "language_model.model.layers.34.self_attn.query_key_value.bias": "pytorch_model-00009-of-00011.bin",
473
+ "language_model.model.layers.34.self_attn.query_key_value.weight": "pytorch_model-00009-of-00011.bin",
474
+ "language_model.model.layers.35.input_layernorm.bias": "pytorch_model-00009-of-00011.bin",
475
+ "language_model.model.layers.35.input_layernorm.weight": "pytorch_model-00009-of-00011.bin",
476
+ "language_model.model.layers.35.mlp.dense_4h_to_h.bias": "pytorch_model-00009-of-00011.bin",
477
+ "language_model.model.layers.35.mlp.dense_4h_to_h.weight": "pytorch_model-00009-of-00011.bin",
478
+ "language_model.model.layers.35.mlp.dense_h_to_4h.bias": "pytorch_model-00009-of-00011.bin",
479
+ "language_model.model.layers.35.mlp.dense_h_to_4h.weight": "pytorch_model-00009-of-00011.bin",
480
+ "language_model.model.layers.35.post_attention_layernorm.bias": "pytorch_model-00009-of-00011.bin",
481
+ "language_model.model.layers.35.post_attention_layernorm.weight": "pytorch_model-00009-of-00011.bin",
482
+ "language_model.model.layers.35.self_attn.dense.bias": "pytorch_model-00009-of-00011.bin",
483
+ "language_model.model.layers.35.self_attn.dense.weight": "pytorch_model-00009-of-00011.bin",
484
+ "language_model.model.layers.35.self_attn.k_layernorm.bias": "pytorch_model-00009-of-00011.bin",
485
+ "language_model.model.layers.35.self_attn.k_layernorm.weight": "pytorch_model-00009-of-00011.bin",
486
+ "language_model.model.layers.35.self_attn.q_layernorm.bias": "pytorch_model-00009-of-00011.bin",
487
+ "language_model.model.layers.35.self_attn.q_layernorm.weight": "pytorch_model-00009-of-00011.bin",
488
+ "language_model.model.layers.35.self_attn.query_key_value.bias": "pytorch_model-00009-of-00011.bin",
489
+ "language_model.model.layers.35.self_attn.query_key_value.weight": "pytorch_model-00009-of-00011.bin",
490
+ "language_model.model.layers.4.input_layernorm.bias": "pytorch_model-00003-of-00011.bin",
491
+ "language_model.model.layers.4.input_layernorm.weight": "pytorch_model-00003-of-00011.bin",
492
+ "language_model.model.layers.4.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00011.bin",
493
+ "language_model.model.layers.4.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00011.bin",
494
+ "language_model.model.layers.4.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00011.bin",
495
+ "language_model.model.layers.4.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00011.bin",
496
+ "language_model.model.layers.4.post_attention_layernorm.bias": "pytorch_model-00003-of-00011.bin",
497
+ "language_model.model.layers.4.post_attention_layernorm.weight": "pytorch_model-00003-of-00011.bin",
498
+ "language_model.model.layers.4.self_attn.dense.bias": "pytorch_model-00002-of-00011.bin",
499
+ "language_model.model.layers.4.self_attn.dense.weight": "pytorch_model-00002-of-00011.bin",
500
+ "language_model.model.layers.4.self_attn.k_layernorm.bias": "pytorch_model-00002-of-00011.bin",
501
+ "language_model.model.layers.4.self_attn.k_layernorm.weight": "pytorch_model-00002-of-00011.bin",
502
+ "language_model.model.layers.4.self_attn.q_layernorm.bias": "pytorch_model-00002-of-00011.bin",
503
+ "language_model.model.layers.4.self_attn.q_layernorm.weight": "pytorch_model-00002-of-00011.bin",
504
+ "language_model.model.layers.4.self_attn.query_key_value.bias": "pytorch_model-00002-of-00011.bin",
505
+ "language_model.model.layers.4.self_attn.query_key_value.weight": "pytorch_model-00002-of-00011.bin",
506
+ "language_model.model.layers.5.input_layernorm.bias": "pytorch_model-00003-of-00011.bin",
507
+ "language_model.model.layers.5.input_layernorm.weight": "pytorch_model-00003-of-00011.bin",
508
+ "language_model.model.layers.5.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00011.bin",
509
+ "language_model.model.layers.5.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00011.bin",
510
+ "language_model.model.layers.5.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00011.bin",
511
+ "language_model.model.layers.5.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00011.bin",
512
+ "language_model.model.layers.5.post_attention_layernorm.bias": "pytorch_model-00003-of-00011.bin",
513
+ "language_model.model.layers.5.post_attention_layernorm.weight": "pytorch_model-00003-of-00011.bin",
514
+ "language_model.model.layers.5.self_attn.dense.bias": "pytorch_model-00003-of-00011.bin",
515
+ "language_model.model.layers.5.self_attn.dense.weight": "pytorch_model-00003-of-00011.bin",
516
+ "language_model.model.layers.5.self_attn.k_layernorm.bias": "pytorch_model-00003-of-00011.bin",
517
+ "language_model.model.layers.5.self_attn.k_layernorm.weight": "pytorch_model-00003-of-00011.bin",
518
+ "language_model.model.layers.5.self_attn.q_layernorm.bias": "pytorch_model-00003-of-00011.bin",
519
+ "language_model.model.layers.5.self_attn.q_layernorm.weight": "pytorch_model-00003-of-00011.bin",
520
+ "language_model.model.layers.5.self_attn.query_key_value.bias": "pytorch_model-00003-of-00011.bin",
521
+ "language_model.model.layers.5.self_attn.query_key_value.weight": "pytorch_model-00003-of-00011.bin",
522
+ "language_model.model.layers.6.input_layernorm.bias": "pytorch_model-00003-of-00011.bin",
523
+ "language_model.model.layers.6.input_layernorm.weight": "pytorch_model-00003-of-00011.bin",
524
+ "language_model.model.layers.6.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00011.bin",
525
+ "language_model.model.layers.6.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00011.bin",
526
+ "language_model.model.layers.6.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00011.bin",
527
+ "language_model.model.layers.6.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00011.bin",
528
+ "language_model.model.layers.6.post_attention_layernorm.bias": "pytorch_model-00003-of-00011.bin",
529
+ "language_model.model.layers.6.post_attention_layernorm.weight": "pytorch_model-00003-of-00011.bin",
530
+ "language_model.model.layers.6.self_attn.dense.bias": "pytorch_model-00003-of-00011.bin",
531
+ "language_model.model.layers.6.self_attn.dense.weight": "pytorch_model-00003-of-00011.bin",
532
+ "language_model.model.layers.6.self_attn.k_layernorm.bias": "pytorch_model-00003-of-00011.bin",
533
+ "language_model.model.layers.6.self_attn.k_layernorm.weight": "pytorch_model-00003-of-00011.bin",
534
+ "language_model.model.layers.6.self_attn.q_layernorm.bias": "pytorch_model-00003-of-00011.bin",
535
+ "language_model.model.layers.6.self_attn.q_layernorm.weight": "pytorch_model-00003-of-00011.bin",
536
+ "language_model.model.layers.6.self_attn.query_key_value.bias": "pytorch_model-00003-of-00011.bin",
537
+ "language_model.model.layers.6.self_attn.query_key_value.weight": "pytorch_model-00003-of-00011.bin",
538
+ "language_model.model.layers.7.input_layernorm.bias": "pytorch_model-00003-of-00011.bin",
539
+ "language_model.model.layers.7.input_layernorm.weight": "pytorch_model-00003-of-00011.bin",
540
+ "language_model.model.layers.7.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00011.bin",
541
+ "language_model.model.layers.7.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00011.bin",
542
+ "language_model.model.layers.7.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00011.bin",
543
+ "language_model.model.layers.7.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00011.bin",
544
+ "language_model.model.layers.7.post_attention_layernorm.bias": "pytorch_model-00003-of-00011.bin",
545
+ "language_model.model.layers.7.post_attention_layernorm.weight": "pytorch_model-00003-of-00011.bin",
546
+ "language_model.model.layers.7.self_attn.dense.bias": "pytorch_model-00003-of-00011.bin",
547
+ "language_model.model.layers.7.self_attn.dense.weight": "pytorch_model-00003-of-00011.bin",
548
+ "language_model.model.layers.7.self_attn.k_layernorm.bias": "pytorch_model-00003-of-00011.bin",
549
+ "language_model.model.layers.7.self_attn.k_layernorm.weight": "pytorch_model-00003-of-00011.bin",
550
+ "language_model.model.layers.7.self_attn.q_layernorm.bias": "pytorch_model-00003-of-00011.bin",
551
+ "language_model.model.layers.7.self_attn.q_layernorm.weight": "pytorch_model-00003-of-00011.bin",
552
+ "language_model.model.layers.7.self_attn.query_key_value.bias": "pytorch_model-00003-of-00011.bin",
553
+ "language_model.model.layers.7.self_attn.query_key_value.weight": "pytorch_model-00003-of-00011.bin",
554
+ "language_model.model.layers.8.input_layernorm.bias": "pytorch_model-00003-of-00011.bin",
555
+ "language_model.model.layers.8.input_layernorm.weight": "pytorch_model-00003-of-00011.bin",
556
+ "language_model.model.layers.8.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00011.bin",
557
+ "language_model.model.layers.8.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00011.bin",
558
+ "language_model.model.layers.8.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00011.bin",
559
+ "language_model.model.layers.8.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00011.bin",
560
+ "language_model.model.layers.8.post_attention_layernorm.bias": "pytorch_model-00003-of-00011.bin",
561
+ "language_model.model.layers.8.post_attention_layernorm.weight": "pytorch_model-00003-of-00011.bin",
562
+ "language_model.model.layers.8.self_attn.dense.bias": "pytorch_model-00003-of-00011.bin",
563
+ "language_model.model.layers.8.self_attn.dense.weight": "pytorch_model-00003-of-00011.bin",
564
+ "language_model.model.layers.8.self_attn.k_layernorm.bias": "pytorch_model-00003-of-00011.bin",
565
+ "language_model.model.layers.8.self_attn.k_layernorm.weight": "pytorch_model-00003-of-00011.bin",
566
+ "language_model.model.layers.8.self_attn.q_layernorm.bias": "pytorch_model-00003-of-00011.bin",
567
+ "language_model.model.layers.8.self_attn.q_layernorm.weight": "pytorch_model-00003-of-00011.bin",
568
+ "language_model.model.layers.8.self_attn.query_key_value.bias": "pytorch_model-00003-of-00011.bin",
569
+ "language_model.model.layers.8.self_attn.query_key_value.weight": "pytorch_model-00003-of-00011.bin",
570
+ "language_model.model.layers.9.input_layernorm.bias": "pytorch_model-00004-of-00011.bin",
571
+ "language_model.model.layers.9.input_layernorm.weight": "pytorch_model-00004-of-00011.bin",
572
+ "language_model.model.layers.9.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00011.bin",
573
+ "language_model.model.layers.9.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00011.bin",
574
+ "language_model.model.layers.9.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00011.bin",
575
+ "language_model.model.layers.9.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00011.bin",
576
+ "language_model.model.layers.9.post_attention_layernorm.bias": "pytorch_model-00004-of-00011.bin",
577
+ "language_model.model.layers.9.post_attention_layernorm.weight": "pytorch_model-00004-of-00011.bin",
578
+ "language_model.model.layers.9.self_attn.dense.bias": "pytorch_model-00003-of-00011.bin",
579
+ "language_model.model.layers.9.self_attn.dense.weight": "pytorch_model-00003-of-00011.bin",
580
+ "language_model.model.layers.9.self_attn.k_layernorm.bias": "pytorch_model-00003-of-00011.bin",
581
+ "language_model.model.layers.9.self_attn.k_layernorm.weight": "pytorch_model-00003-of-00011.bin",
582
+ "language_model.model.layers.9.self_attn.q_layernorm.bias": "pytorch_model-00003-of-00011.bin",
583
+ "language_model.model.layers.9.self_attn.q_layernorm.weight": "pytorch_model-00003-of-00011.bin",
584
+ "language_model.model.layers.9.self_attn.query_key_value.bias": "pytorch_model-00003-of-00011.bin",
585
+ "language_model.model.layers.9.self_attn.query_key_value.weight": "pytorch_model-00003-of-00011.bin",
586
+ "vision_embed_tokens.bias": "pytorch_model-00011-of-00011.bin",
587
+ "vision_embed_tokens.weight": "pytorch_model-00011-of-00011.bin"
588
+ }
589
+ }