jonabur commited on
Commit
2955bc8
•
1 Parent(s): c275bda

update to safetensors

Browse files
config.json CHANGED
@@ -20,7 +20,7 @@
20
  "pretraining_tp": 2,
21
  "slow_but_exact": false,
22
  "torch_dtype": "bfloat16",
23
- "transformers_version": "4.33.0",
24
  "use_cache": true,
25
  "vocab_size": 128000
26
  }
 
20
  "pretraining_tp": 2,
21
  "slow_but_exact": false,
22
  "torch_dtype": "bfloat16",
23
+ "transformers_version": "4.35.0",
24
  "use_cache": true,
25
  "vocab_size": 128000
26
  }
generation_config.json CHANGED
@@ -3,5 +3,5 @@
3
  "bos_token_id": 1,
4
  "eos_token_id": 2,
5
  "pad_token_id": 3,
6
- "transformers_version": "4.33.0"
7
  }
 
3
  "bos_token_id": 1,
4
  "eos_token_id": 2,
5
  "pad_token_id": 3,
6
+ "transformers_version": "4.35.0"
7
  }
pytorch_model-00001-of-00007.bin → model-00001-of-00014.safetensors RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ea7b34c5d10905d088adee170496022e19356119b8c061244f0ca8dd6a346f7e
3
- size 9646093541
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a428a9a9062246860b2917ceab30f73f3a5c1153eb197bfe9a30c5ebddc60c1
3
+ size 4712820784
pytorch_model-00002-of-00007.bin → model-00002-of-00014.safetensors RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:41c165ec9533b91e3c937c13a36764c88ee138e20305620bafc54c7b3e1337d5
3
- size 9866528411
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c6401e37e5a485c026dfae1e244f80bf2081e4a6d0fc8343603d9c614118a08
3
+ size 4933252680
pytorch_model-00003-of-00007.bin → model-00003-of-00014.safetensors RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9934f122609e847c516043b957242335f51550aa744b6de847eaac5d1bfc3fa6
3
- size 9866528411
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c648796fb63476f607ae4e398d83396a5cc35eb6c4f0ab30640aa9b22c0581c
3
+ size 4933252648
pytorch_model-00004-of-00007.bin → model-00004-of-00014.safetensors RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:01c530bf84ff6cb393969a7a43a711532233c46845c940cfef4fabaf505a5662
3
- size 9866528411
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8de0fe06a8de40918fcaad9887b3adac3405e03777083d9618345b0f663789d8
3
+ size 4933252728
model-00005-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37619b4a4e4b2b71af9de8c6bcb86aeacb4b40461f60bdd6b226d89f2a4a4ea3
3
+ size 4933252728
model-00006-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9879dde82f1c270a740ba0befda8628f884e71145bf1f395e7d7c9179fd35035
3
+ size 4933252728
model-00007-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02371b39cf036f6a3f0880f12807b4e8a7d8a87205cd0b68ff9426ce899d4013
3
+ size 4933252728
model-00008-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2e78b8ac923df9e6a784991a676011888826b64a13bda771a3c55645ba543fb
3
+ size 4933252728
model-00009-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ddd8d5149d814c1cc04d6932443de48d30f9ed1c5de5cecda39dae70e097cb1
3
+ size 4933252728
model-00010-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54320c19889e7fd54d1cea7b401cf70aab945a28781e22cdb9e1a9a6f4c72604
3
+ size 4933252728
model-00011-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e2f8f33b7412faf1307f2c8b326a486a7f90a4a2d7ff380d9df2180dcac84c5
3
+ size 4933252728
model-00012-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:951f9e97999518b9ef53258385bf7fabbddd72523e986caa3e0410e2c2e43be2
3
+ size 4933252728
model-00013-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a0cae7c5c2ac94aaf579b69da4b9d4f3d1529a60b166b917e4b56b00f709471
3
+ size 4933252728
model-00014-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af197ef3a06056365e5d5bfe51c2ac4737185d513ece4b123e58f9f1b383a20f
3
+ size 4522124144
model.safetensors.index.json ADDED
@@ -0,0 +1,660 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 68433899520
4
+ },
5
+ "weight_map": {
6
+ "transformer.h.0.input_layernorm.bias": "model-00001-of-00014.safetensors",
7
+ "transformer.h.0.input_layernorm.weight": "model-00001-of-00014.safetensors",
8
+ "transformer.h.0.mlp.dense_4h_to_h.bias": "model-00001-of-00014.safetensors",
9
+ "transformer.h.0.mlp.dense_4h_to_h.weight": "model-00001-of-00014.safetensors",
10
+ "transformer.h.0.mlp.dense_h_to_4h.bias": "model-00001-of-00014.safetensors",
11
+ "transformer.h.0.mlp.dense_h_to_4h.weight": "model-00001-of-00014.safetensors",
12
+ "transformer.h.0.post_attention_layernorm.bias": "model-00001-of-00014.safetensors",
13
+ "transformer.h.0.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
14
+ "transformer.h.0.self_attention.dense.bias": "model-00001-of-00014.safetensors",
15
+ "transformer.h.0.self_attention.dense.weight": "model-00001-of-00014.safetensors",
16
+ "transformer.h.0.self_attention.query_key_value.bias": "model-00001-of-00014.safetensors",
17
+ "transformer.h.0.self_attention.query_key_value.weight": "model-00001-of-00014.safetensors",
18
+ "transformer.h.1.input_layernorm.bias": "model-00001-of-00014.safetensors",
19
+ "transformer.h.1.input_layernorm.weight": "model-00001-of-00014.safetensors",
20
+ "transformer.h.1.mlp.dense_4h_to_h.bias": "model-00001-of-00014.safetensors",
21
+ "transformer.h.1.mlp.dense_4h_to_h.weight": "model-00001-of-00014.safetensors",
22
+ "transformer.h.1.mlp.dense_h_to_4h.bias": "model-00001-of-00014.safetensors",
23
+ "transformer.h.1.mlp.dense_h_to_4h.weight": "model-00001-of-00014.safetensors",
24
+ "transformer.h.1.post_attention_layernorm.bias": "model-00001-of-00014.safetensors",
25
+ "transformer.h.1.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
26
+ "transformer.h.1.self_attention.dense.bias": "model-00001-of-00014.safetensors",
27
+ "transformer.h.1.self_attention.dense.weight": "model-00001-of-00014.safetensors",
28
+ "transformer.h.1.self_attention.query_key_value.bias": "model-00001-of-00014.safetensors",
29
+ "transformer.h.1.self_attention.query_key_value.weight": "model-00001-of-00014.safetensors",
30
+ "transformer.h.10.input_layernorm.bias": "model-00003-of-00014.safetensors",
31
+ "transformer.h.10.input_layernorm.weight": "model-00003-of-00014.safetensors",
32
+ "transformer.h.10.mlp.dense_4h_to_h.bias": "model-00004-of-00014.safetensors",
33
+ "transformer.h.10.mlp.dense_4h_to_h.weight": "model-00004-of-00014.safetensors",
34
+ "transformer.h.10.mlp.dense_h_to_4h.bias": "model-00004-of-00014.safetensors",
35
+ "transformer.h.10.mlp.dense_h_to_4h.weight": "model-00004-of-00014.safetensors",
36
+ "transformer.h.10.post_attention_layernorm.bias": "model-00003-of-00014.safetensors",
37
+ "transformer.h.10.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
38
+ "transformer.h.10.self_attention.dense.bias": "model-00003-of-00014.safetensors",
39
+ "transformer.h.10.self_attention.dense.weight": "model-00003-of-00014.safetensors",
40
+ "transformer.h.10.self_attention.query_key_value.bias": "model-00003-of-00014.safetensors",
41
+ "transformer.h.10.self_attention.query_key_value.weight": "model-00003-of-00014.safetensors",
42
+ "transformer.h.11.input_layernorm.bias": "model-00004-of-00014.safetensors",
43
+ "transformer.h.11.input_layernorm.weight": "model-00004-of-00014.safetensors",
44
+ "transformer.h.11.mlp.dense_4h_to_h.bias": "model-00004-of-00014.safetensors",
45
+ "transformer.h.11.mlp.dense_4h_to_h.weight": "model-00004-of-00014.safetensors",
46
+ "transformer.h.11.mlp.dense_h_to_4h.bias": "model-00004-of-00014.safetensors",
47
+ "transformer.h.11.mlp.dense_h_to_4h.weight": "model-00004-of-00014.safetensors",
48
+ "transformer.h.11.post_attention_layernorm.bias": "model-00004-of-00014.safetensors",
49
+ "transformer.h.11.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
50
+ "transformer.h.11.self_attention.dense.bias": "model-00004-of-00014.safetensors",
51
+ "transformer.h.11.self_attention.dense.weight": "model-00004-of-00014.safetensors",
52
+ "transformer.h.11.self_attention.query_key_value.bias": "model-00004-of-00014.safetensors",
53
+ "transformer.h.11.self_attention.query_key_value.weight": "model-00004-of-00014.safetensors",
54
+ "transformer.h.12.input_layernorm.bias": "model-00004-of-00014.safetensors",
55
+ "transformer.h.12.input_layernorm.weight": "model-00004-of-00014.safetensors",
56
+ "transformer.h.12.mlp.dense_4h_to_h.bias": "model-00004-of-00014.safetensors",
57
+ "transformer.h.12.mlp.dense_4h_to_h.weight": "model-00004-of-00014.safetensors",
58
+ "transformer.h.12.mlp.dense_h_to_4h.bias": "model-00004-of-00014.safetensors",
59
+ "transformer.h.12.mlp.dense_h_to_4h.weight": "model-00004-of-00014.safetensors",
60
+ "transformer.h.12.post_attention_layernorm.bias": "model-00004-of-00014.safetensors",
61
+ "transformer.h.12.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
62
+ "transformer.h.12.self_attention.dense.bias": "model-00004-of-00014.safetensors",
63
+ "transformer.h.12.self_attention.dense.weight": "model-00004-of-00014.safetensors",
64
+ "transformer.h.12.self_attention.query_key_value.bias": "model-00004-of-00014.safetensors",
65
+ "transformer.h.12.self_attention.query_key_value.weight": "model-00004-of-00014.safetensors",
66
+ "transformer.h.13.input_layernorm.bias": "model-00004-of-00014.safetensors",
67
+ "transformer.h.13.input_layernorm.weight": "model-00004-of-00014.safetensors",
68
+ "transformer.h.13.mlp.dense_4h_to_h.bias": "model-00004-of-00014.safetensors",
69
+ "transformer.h.13.mlp.dense_4h_to_h.weight": "model-00004-of-00014.safetensors",
70
+ "transformer.h.13.mlp.dense_h_to_4h.bias": "model-00004-of-00014.safetensors",
71
+ "transformer.h.13.mlp.dense_h_to_4h.weight": "model-00004-of-00014.safetensors",
72
+ "transformer.h.13.post_attention_layernorm.bias": "model-00004-of-00014.safetensors",
73
+ "transformer.h.13.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
74
+ "transformer.h.13.self_attention.dense.bias": "model-00004-of-00014.safetensors",
75
+ "transformer.h.13.self_attention.dense.weight": "model-00004-of-00014.safetensors",
76
+ "transformer.h.13.self_attention.query_key_value.bias": "model-00004-of-00014.safetensors",
77
+ "transformer.h.13.self_attention.query_key_value.weight": "model-00004-of-00014.safetensors",
78
+ "transformer.h.14.input_layernorm.bias": "model-00004-of-00014.safetensors",
79
+ "transformer.h.14.input_layernorm.weight": "model-00004-of-00014.safetensors",
80
+ "transformer.h.14.mlp.dense_4h_to_h.bias": "model-00005-of-00014.safetensors",
81
+ "transformer.h.14.mlp.dense_4h_to_h.weight": "model-00005-of-00014.safetensors",
82
+ "transformer.h.14.mlp.dense_h_to_4h.bias": "model-00005-of-00014.safetensors",
83
+ "transformer.h.14.mlp.dense_h_to_4h.weight": "model-00005-of-00014.safetensors",
84
+ "transformer.h.14.post_attention_layernorm.bias": "model-00004-of-00014.safetensors",
85
+ "transformer.h.14.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
86
+ "transformer.h.14.self_attention.dense.bias": "model-00004-of-00014.safetensors",
87
+ "transformer.h.14.self_attention.dense.weight": "model-00004-of-00014.safetensors",
88
+ "transformer.h.14.self_attention.query_key_value.bias": "model-00004-of-00014.safetensors",
89
+ "transformer.h.14.self_attention.query_key_value.weight": "model-00004-of-00014.safetensors",
90
+ "transformer.h.15.input_layernorm.bias": "model-00005-of-00014.safetensors",
91
+ "transformer.h.15.input_layernorm.weight": "model-00005-of-00014.safetensors",
92
+ "transformer.h.15.mlp.dense_4h_to_h.bias": "model-00005-of-00014.safetensors",
93
+ "transformer.h.15.mlp.dense_4h_to_h.weight": "model-00005-of-00014.safetensors",
94
+ "transformer.h.15.mlp.dense_h_to_4h.bias": "model-00005-of-00014.safetensors",
95
+ "transformer.h.15.mlp.dense_h_to_4h.weight": "model-00005-of-00014.safetensors",
96
+ "transformer.h.15.post_attention_layernorm.bias": "model-00005-of-00014.safetensors",
97
+ "transformer.h.15.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
98
+ "transformer.h.15.self_attention.dense.bias": "model-00005-of-00014.safetensors",
99
+ "transformer.h.15.self_attention.dense.weight": "model-00005-of-00014.safetensors",
100
+ "transformer.h.15.self_attention.query_key_value.bias": "model-00005-of-00014.safetensors",
101
+ "transformer.h.15.self_attention.query_key_value.weight": "model-00005-of-00014.safetensors",
102
+ "transformer.h.16.input_layernorm.bias": "model-00005-of-00014.safetensors",
103
+ "transformer.h.16.input_layernorm.weight": "model-00005-of-00014.safetensors",
104
+ "transformer.h.16.mlp.dense_4h_to_h.bias": "model-00005-of-00014.safetensors",
105
+ "transformer.h.16.mlp.dense_4h_to_h.weight": "model-00005-of-00014.safetensors",
106
+ "transformer.h.16.mlp.dense_h_to_4h.bias": "model-00005-of-00014.safetensors",
107
+ "transformer.h.16.mlp.dense_h_to_4h.weight": "model-00005-of-00014.safetensors",
108
+ "transformer.h.16.post_attention_layernorm.bias": "model-00005-of-00014.safetensors",
109
+ "transformer.h.16.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
110
+ "transformer.h.16.self_attention.dense.bias": "model-00005-of-00014.safetensors",
111
+ "transformer.h.16.self_attention.dense.weight": "model-00005-of-00014.safetensors",
112
+ "transformer.h.16.self_attention.query_key_value.bias": "model-00005-of-00014.safetensors",
113
+ "transformer.h.16.self_attention.query_key_value.weight": "model-00005-of-00014.safetensors",
114
+ "transformer.h.17.input_layernorm.bias": "model-00005-of-00014.safetensors",
115
+ "transformer.h.17.input_layernorm.weight": "model-00005-of-00014.safetensors",
116
+ "transformer.h.17.mlp.dense_4h_to_h.bias": "model-00005-of-00014.safetensors",
117
+ "transformer.h.17.mlp.dense_4h_to_h.weight": "model-00005-of-00014.safetensors",
118
+ "transformer.h.17.mlp.dense_h_to_4h.bias": "model-00005-of-00014.safetensors",
119
+ "transformer.h.17.mlp.dense_h_to_4h.weight": "model-00005-of-00014.safetensors",
120
+ "transformer.h.17.post_attention_layernorm.bias": "model-00005-of-00014.safetensors",
121
+ "transformer.h.17.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
122
+ "transformer.h.17.self_attention.dense.bias": "model-00005-of-00014.safetensors",
123
+ "transformer.h.17.self_attention.dense.weight": "model-00005-of-00014.safetensors",
124
+ "transformer.h.17.self_attention.query_key_value.bias": "model-00005-of-00014.safetensors",
125
+ "transformer.h.17.self_attention.query_key_value.weight": "model-00005-of-00014.safetensors",
126
+ "transformer.h.18.input_layernorm.bias": "model-00005-of-00014.safetensors",
127
+ "transformer.h.18.input_layernorm.weight": "model-00005-of-00014.safetensors",
128
+ "transformer.h.18.mlp.dense_4h_to_h.bias": "model-00006-of-00014.safetensors",
129
+ "transformer.h.18.mlp.dense_4h_to_h.weight": "model-00006-of-00014.safetensors",
130
+ "transformer.h.18.mlp.dense_h_to_4h.bias": "model-00006-of-00014.safetensors",
131
+ "transformer.h.18.mlp.dense_h_to_4h.weight": "model-00006-of-00014.safetensors",
132
+ "transformer.h.18.post_attention_layernorm.bias": "model-00005-of-00014.safetensors",
133
+ "transformer.h.18.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
134
+ "transformer.h.18.self_attention.dense.bias": "model-00005-of-00014.safetensors",
135
+ "transformer.h.18.self_attention.dense.weight": "model-00005-of-00014.safetensors",
136
+ "transformer.h.18.self_attention.query_key_value.bias": "model-00005-of-00014.safetensors",
137
+ "transformer.h.18.self_attention.query_key_value.weight": "model-00005-of-00014.safetensors",
138
+ "transformer.h.19.input_layernorm.bias": "model-00006-of-00014.safetensors",
139
+ "transformer.h.19.input_layernorm.weight": "model-00006-of-00014.safetensors",
140
+ "transformer.h.19.mlp.dense_4h_to_h.bias": "model-00006-of-00014.safetensors",
141
+ "transformer.h.19.mlp.dense_4h_to_h.weight": "model-00006-of-00014.safetensors",
142
+ "transformer.h.19.mlp.dense_h_to_4h.bias": "model-00006-of-00014.safetensors",
143
+ "transformer.h.19.mlp.dense_h_to_4h.weight": "model-00006-of-00014.safetensors",
144
+ "transformer.h.19.post_attention_layernorm.bias": "model-00006-of-00014.safetensors",
145
+ "transformer.h.19.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
146
+ "transformer.h.19.self_attention.dense.bias": "model-00006-of-00014.safetensors",
147
+ "transformer.h.19.self_attention.dense.weight": "model-00006-of-00014.safetensors",
148
+ "transformer.h.19.self_attention.query_key_value.bias": "model-00006-of-00014.safetensors",
149
+ "transformer.h.19.self_attention.query_key_value.weight": "model-00006-of-00014.safetensors",
150
+ "transformer.h.2.input_layernorm.bias": "model-00001-of-00014.safetensors",
151
+ "transformer.h.2.input_layernorm.weight": "model-00001-of-00014.safetensors",
152
+ "transformer.h.2.mlp.dense_4h_to_h.bias": "model-00002-of-00014.safetensors",
153
+ "transformer.h.2.mlp.dense_4h_to_h.weight": "model-00002-of-00014.safetensors",
154
+ "transformer.h.2.mlp.dense_h_to_4h.bias": "model-00002-of-00014.safetensors",
155
+ "transformer.h.2.mlp.dense_h_to_4h.weight": "model-00002-of-00014.safetensors",
156
+ "transformer.h.2.post_attention_layernorm.bias": "model-00001-of-00014.safetensors",
157
+ "transformer.h.2.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
158
+ "transformer.h.2.self_attention.dense.bias": "model-00001-of-00014.safetensors",
159
+ "transformer.h.2.self_attention.dense.weight": "model-00001-of-00014.safetensors",
160
+ "transformer.h.2.self_attention.query_key_value.bias": "model-00001-of-00014.safetensors",
161
+ "transformer.h.2.self_attention.query_key_value.weight": "model-00001-of-00014.safetensors",
162
+ "transformer.h.20.input_layernorm.bias": "model-00006-of-00014.safetensors",
163
+ "transformer.h.20.input_layernorm.weight": "model-00006-of-00014.safetensors",
164
+ "transformer.h.20.mlp.dense_4h_to_h.bias": "model-00006-of-00014.safetensors",
165
+ "transformer.h.20.mlp.dense_4h_to_h.weight": "model-00006-of-00014.safetensors",
166
+ "transformer.h.20.mlp.dense_h_to_4h.bias": "model-00006-of-00014.safetensors",
167
+ "transformer.h.20.mlp.dense_h_to_4h.weight": "model-00006-of-00014.safetensors",
168
+ "transformer.h.20.post_attention_layernorm.bias": "model-00006-of-00014.safetensors",
169
+ "transformer.h.20.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
170
+ "transformer.h.20.self_attention.dense.bias": "model-00006-of-00014.safetensors",
171
+ "transformer.h.20.self_attention.dense.weight": "model-00006-of-00014.safetensors",
172
+ "transformer.h.20.self_attention.query_key_value.bias": "model-00006-of-00014.safetensors",
173
+ "transformer.h.20.self_attention.query_key_value.weight": "model-00006-of-00014.safetensors",
174
+ "transformer.h.21.input_layernorm.bias": "model-00006-of-00014.safetensors",
175
+ "transformer.h.21.input_layernorm.weight": "model-00006-of-00014.safetensors",
176
+ "transformer.h.21.mlp.dense_4h_to_h.bias": "model-00006-of-00014.safetensors",
177
+ "transformer.h.21.mlp.dense_4h_to_h.weight": "model-00006-of-00014.safetensors",
178
+ "transformer.h.21.mlp.dense_h_to_4h.bias": "model-00006-of-00014.safetensors",
179
+ "transformer.h.21.mlp.dense_h_to_4h.weight": "model-00006-of-00014.safetensors",
180
+ "transformer.h.21.post_attention_layernorm.bias": "model-00006-of-00014.safetensors",
181
+ "transformer.h.21.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
182
+ "transformer.h.21.self_attention.dense.bias": "model-00006-of-00014.safetensors",
183
+ "transformer.h.21.self_attention.dense.weight": "model-00006-of-00014.safetensors",
184
+ "transformer.h.21.self_attention.query_key_value.bias": "model-00006-of-00014.safetensors",
185
+ "transformer.h.21.self_attention.query_key_value.weight": "model-00006-of-00014.safetensors",
186
+ "transformer.h.22.input_layernorm.bias": "model-00006-of-00014.safetensors",
187
+ "transformer.h.22.input_layernorm.weight": "model-00006-of-00014.safetensors",
188
+ "transformer.h.22.mlp.dense_4h_to_h.bias": "model-00007-of-00014.safetensors",
189
+ "transformer.h.22.mlp.dense_4h_to_h.weight": "model-00007-of-00014.safetensors",
190
+ "transformer.h.22.mlp.dense_h_to_4h.bias": "model-00007-of-00014.safetensors",
191
+ "transformer.h.22.mlp.dense_h_to_4h.weight": "model-00007-of-00014.safetensors",
192
+ "transformer.h.22.post_attention_layernorm.bias": "model-00006-of-00014.safetensors",
193
+ "transformer.h.22.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
194
+ "transformer.h.22.self_attention.dense.bias": "model-00006-of-00014.safetensors",
195
+ "transformer.h.22.self_attention.dense.weight": "model-00006-of-00014.safetensors",
196
+ "transformer.h.22.self_attention.query_key_value.bias": "model-00006-of-00014.safetensors",
197
+ "transformer.h.22.self_attention.query_key_value.weight": "model-00006-of-00014.safetensors",
198
+ "transformer.h.23.input_layernorm.bias": "model-00007-of-00014.safetensors",
199
+ "transformer.h.23.input_layernorm.weight": "model-00007-of-00014.safetensors",
200
+ "transformer.h.23.mlp.dense_4h_to_h.bias": "model-00007-of-00014.safetensors",
201
+ "transformer.h.23.mlp.dense_4h_to_h.weight": "model-00007-of-00014.safetensors",
202
+ "transformer.h.23.mlp.dense_h_to_4h.bias": "model-00007-of-00014.safetensors",
203
+ "transformer.h.23.mlp.dense_h_to_4h.weight": "model-00007-of-00014.safetensors",
204
+ "transformer.h.23.post_attention_layernorm.bias": "model-00007-of-00014.safetensors",
205
+ "transformer.h.23.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
206
+ "transformer.h.23.self_attention.dense.bias": "model-00007-of-00014.safetensors",
207
+ "transformer.h.23.self_attention.dense.weight": "model-00007-of-00014.safetensors",
208
+ "transformer.h.23.self_attention.query_key_value.bias": "model-00007-of-00014.safetensors",
209
+ "transformer.h.23.self_attention.query_key_value.weight": "model-00007-of-00014.safetensors",
210
+ "transformer.h.24.input_layernorm.bias": "model-00007-of-00014.safetensors",
211
+ "transformer.h.24.input_layernorm.weight": "model-00007-of-00014.safetensors",
212
+ "transformer.h.24.mlp.dense_4h_to_h.bias": "model-00007-of-00014.safetensors",
213
+ "transformer.h.24.mlp.dense_4h_to_h.weight": "model-00007-of-00014.safetensors",
214
+ "transformer.h.24.mlp.dense_h_to_4h.bias": "model-00007-of-00014.safetensors",
215
+ "transformer.h.24.mlp.dense_h_to_4h.weight": "model-00007-of-00014.safetensors",
216
+ "transformer.h.24.post_attention_layernorm.bias": "model-00007-of-00014.safetensors",
217
+ "transformer.h.24.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
218
+ "transformer.h.24.self_attention.dense.bias": "model-00007-of-00014.safetensors",
219
+ "transformer.h.24.self_attention.dense.weight": "model-00007-of-00014.safetensors",
220
+ "transformer.h.24.self_attention.query_key_value.bias": "model-00007-of-00014.safetensors",
221
+ "transformer.h.24.self_attention.query_key_value.weight": "model-00007-of-00014.safetensors",
222
+ "transformer.h.25.input_layernorm.bias": "model-00007-of-00014.safetensors",
223
+ "transformer.h.25.input_layernorm.weight": "model-00007-of-00014.safetensors",
224
+ "transformer.h.25.mlp.dense_4h_to_h.bias": "model-00007-of-00014.safetensors",
225
+ "transformer.h.25.mlp.dense_4h_to_h.weight": "model-00007-of-00014.safetensors",
226
+ "transformer.h.25.mlp.dense_h_to_4h.bias": "model-00007-of-00014.safetensors",
227
+ "transformer.h.25.mlp.dense_h_to_4h.weight": "model-00007-of-00014.safetensors",
228
+ "transformer.h.25.post_attention_layernorm.bias": "model-00007-of-00014.safetensors",
229
+ "transformer.h.25.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
230
+ "transformer.h.25.self_attention.dense.bias": "model-00007-of-00014.safetensors",
231
+ "transformer.h.25.self_attention.dense.weight": "model-00007-of-00014.safetensors",
232
+ "transformer.h.25.self_attention.query_key_value.bias": "model-00007-of-00014.safetensors",
233
+ "transformer.h.25.self_attention.query_key_value.weight": "model-00007-of-00014.safetensors",
234
+ "transformer.h.26.input_layernorm.bias": "model-00007-of-00014.safetensors",
235
+ "transformer.h.26.input_layernorm.weight": "model-00007-of-00014.safetensors",
236
+ "transformer.h.26.mlp.dense_4h_to_h.bias": "model-00008-of-00014.safetensors",
237
+ "transformer.h.26.mlp.dense_4h_to_h.weight": "model-00008-of-00014.safetensors",
238
+ "transformer.h.26.mlp.dense_h_to_4h.bias": "model-00008-of-00014.safetensors",
239
+ "transformer.h.26.mlp.dense_h_to_4h.weight": "model-00008-of-00014.safetensors",
240
+ "transformer.h.26.post_attention_layernorm.bias": "model-00007-of-00014.safetensors",
241
+ "transformer.h.26.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
242
+ "transformer.h.26.self_attention.dense.bias": "model-00007-of-00014.safetensors",
243
+ "transformer.h.26.self_attention.dense.weight": "model-00007-of-00014.safetensors",
244
+ "transformer.h.26.self_attention.query_key_value.bias": "model-00007-of-00014.safetensors",
245
+ "transformer.h.26.self_attention.query_key_value.weight": "model-00007-of-00014.safetensors",
246
+ "transformer.h.27.input_layernorm.bias": "model-00008-of-00014.safetensors",
247
+ "transformer.h.27.input_layernorm.weight": "model-00008-of-00014.safetensors",
248
+ "transformer.h.27.mlp.dense_4h_to_h.bias": "model-00008-of-00014.safetensors",
249
+ "transformer.h.27.mlp.dense_4h_to_h.weight": "model-00008-of-00014.safetensors",
250
+ "transformer.h.27.mlp.dense_h_to_4h.bias": "model-00008-of-00014.safetensors",
251
+ "transformer.h.27.mlp.dense_h_to_4h.weight": "model-00008-of-00014.safetensors",
252
+ "transformer.h.27.post_attention_layernorm.bias": "model-00008-of-00014.safetensors",
253
+ "transformer.h.27.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
254
+ "transformer.h.27.self_attention.dense.bias": "model-00008-of-00014.safetensors",
255
+ "transformer.h.27.self_attention.dense.weight": "model-00008-of-00014.safetensors",
256
+ "transformer.h.27.self_attention.query_key_value.bias": "model-00008-of-00014.safetensors",
257
+ "transformer.h.27.self_attention.query_key_value.weight": "model-00008-of-00014.safetensors",
258
+ "transformer.h.28.input_layernorm.bias": "model-00008-of-00014.safetensors",
259
+ "transformer.h.28.input_layernorm.weight": "model-00008-of-00014.safetensors",
260
+ "transformer.h.28.mlp.dense_4h_to_h.bias": "model-00008-of-00014.safetensors",
261
+ "transformer.h.28.mlp.dense_4h_to_h.weight": "model-00008-of-00014.safetensors",
262
+ "transformer.h.28.mlp.dense_h_to_4h.bias": "model-00008-of-00014.safetensors",
263
+ "transformer.h.28.mlp.dense_h_to_4h.weight": "model-00008-of-00014.safetensors",
264
+ "transformer.h.28.post_attention_layernorm.bias": "model-00008-of-00014.safetensors",
265
+ "transformer.h.28.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
266
+ "transformer.h.28.self_attention.dense.bias": "model-00008-of-00014.safetensors",
267
+ "transformer.h.28.self_attention.dense.weight": "model-00008-of-00014.safetensors",
268
+ "transformer.h.28.self_attention.query_key_value.bias": "model-00008-of-00014.safetensors",
269
+ "transformer.h.28.self_attention.query_key_value.weight": "model-00008-of-00014.safetensors",
270
+ "transformer.h.29.input_layernorm.bias": "model-00008-of-00014.safetensors",
271
+ "transformer.h.29.input_layernorm.weight": "model-00008-of-00014.safetensors",
272
+ "transformer.h.29.mlp.dense_4h_to_h.bias": "model-00008-of-00014.safetensors",
273
+ "transformer.h.29.mlp.dense_4h_to_h.weight": "model-00008-of-00014.safetensors",
274
+ "transformer.h.29.mlp.dense_h_to_4h.bias": "model-00008-of-00014.safetensors",
275
+ "transformer.h.29.mlp.dense_h_to_4h.weight": "model-00008-of-00014.safetensors",
276
+ "transformer.h.29.post_attention_layernorm.bias": "model-00008-of-00014.safetensors",
277
+ "transformer.h.29.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
278
+ "transformer.h.29.self_attention.dense.bias": "model-00008-of-00014.safetensors",
279
+ "transformer.h.29.self_attention.dense.weight": "model-00008-of-00014.safetensors",
280
+ "transformer.h.29.self_attention.query_key_value.bias": "model-00008-of-00014.safetensors",
281
+ "transformer.h.29.self_attention.query_key_value.weight": "model-00008-of-00014.safetensors",
282
+ "transformer.h.3.input_layernorm.bias": "model-00002-of-00014.safetensors",
283
+ "transformer.h.3.input_layernorm.weight": "model-00002-of-00014.safetensors",
284
+ "transformer.h.3.mlp.dense_4h_to_h.bias": "model-00002-of-00014.safetensors",
285
+ "transformer.h.3.mlp.dense_4h_to_h.weight": "model-00002-of-00014.safetensors",
286
+ "transformer.h.3.mlp.dense_h_to_4h.bias": "model-00002-of-00014.safetensors",
287
+ "transformer.h.3.mlp.dense_h_to_4h.weight": "model-00002-of-00014.safetensors",
288
+ "transformer.h.3.post_attention_layernorm.bias": "model-00002-of-00014.safetensors",
289
+ "transformer.h.3.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
290
+ "transformer.h.3.self_attention.dense.bias": "model-00002-of-00014.safetensors",
291
+ "transformer.h.3.self_attention.dense.weight": "model-00002-of-00014.safetensors",
292
+ "transformer.h.3.self_attention.query_key_value.bias": "model-00002-of-00014.safetensors",
293
+ "transformer.h.3.self_attention.query_key_value.weight": "model-00002-of-00014.safetensors",
294
+ "transformer.h.30.input_layernorm.bias": "model-00008-of-00014.safetensors",
295
+ "transformer.h.30.input_layernorm.weight": "model-00008-of-00014.safetensors",
296
+ "transformer.h.30.mlp.dense_4h_to_h.bias": "model-00009-of-00014.safetensors",
297
+ "transformer.h.30.mlp.dense_4h_to_h.weight": "model-00009-of-00014.safetensors",
298
+ "transformer.h.30.mlp.dense_h_to_4h.bias": "model-00009-of-00014.safetensors",
299
+ "transformer.h.30.mlp.dense_h_to_4h.weight": "model-00009-of-00014.safetensors",
300
+ "transformer.h.30.post_attention_layernorm.bias": "model-00008-of-00014.safetensors",
301
+ "transformer.h.30.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
302
+ "transformer.h.30.self_attention.dense.bias": "model-00008-of-00014.safetensors",
303
+ "transformer.h.30.self_attention.dense.weight": "model-00008-of-00014.safetensors",
304
+ "transformer.h.30.self_attention.query_key_value.bias": "model-00008-of-00014.safetensors",
305
+ "transformer.h.30.self_attention.query_key_value.weight": "model-00008-of-00014.safetensors",
306
+ "transformer.h.31.input_layernorm.bias": "model-00009-of-00014.safetensors",
307
+ "transformer.h.31.input_layernorm.weight": "model-00009-of-00014.safetensors",
308
+ "transformer.h.31.mlp.dense_4h_to_h.bias": "model-00009-of-00014.safetensors",
309
+ "transformer.h.31.mlp.dense_4h_to_h.weight": "model-00009-of-00014.safetensors",
310
+ "transformer.h.31.mlp.dense_h_to_4h.bias": "model-00009-of-00014.safetensors",
311
+ "transformer.h.31.mlp.dense_h_to_4h.weight": "model-00009-of-00014.safetensors",
312
+ "transformer.h.31.post_attention_layernorm.bias": "model-00009-of-00014.safetensors",
313
+ "transformer.h.31.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
314
+ "transformer.h.31.self_attention.dense.bias": "model-00009-of-00014.safetensors",
315
+ "transformer.h.31.self_attention.dense.weight": "model-00009-of-00014.safetensors",
316
+ "transformer.h.31.self_attention.query_key_value.bias": "model-00009-of-00014.safetensors",
317
+ "transformer.h.31.self_attention.query_key_value.weight": "model-00009-of-00014.safetensors",
318
+ "transformer.h.32.input_layernorm.bias": "model-00009-of-00014.safetensors",
319
+ "transformer.h.32.input_layernorm.weight": "model-00009-of-00014.safetensors",
320
+ "transformer.h.32.mlp.dense_4h_to_h.bias": "model-00009-of-00014.safetensors",
321
+ "transformer.h.32.mlp.dense_4h_to_h.weight": "model-00009-of-00014.safetensors",
322
+ "transformer.h.32.mlp.dense_h_to_4h.bias": "model-00009-of-00014.safetensors",
323
+ "transformer.h.32.mlp.dense_h_to_4h.weight": "model-00009-of-00014.safetensors",
324
+ "transformer.h.32.post_attention_layernorm.bias": "model-00009-of-00014.safetensors",
325
+ "transformer.h.32.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
326
+ "transformer.h.32.self_attention.dense.bias": "model-00009-of-00014.safetensors",
327
+ "transformer.h.32.self_attention.dense.weight": "model-00009-of-00014.safetensors",
328
+ "transformer.h.32.self_attention.query_key_value.bias": "model-00009-of-00014.safetensors",
329
+ "transformer.h.32.self_attention.query_key_value.weight": "model-00009-of-00014.safetensors",
330
+ "transformer.h.33.input_layernorm.bias": "model-00009-of-00014.safetensors",
331
+ "transformer.h.33.input_layernorm.weight": "model-00009-of-00014.safetensors",
332
+ "transformer.h.33.mlp.dense_4h_to_h.bias": "model-00009-of-00014.safetensors",
333
+ "transformer.h.33.mlp.dense_4h_to_h.weight": "model-00009-of-00014.safetensors",
334
+ "transformer.h.33.mlp.dense_h_to_4h.bias": "model-00009-of-00014.safetensors",
335
+ "transformer.h.33.mlp.dense_h_to_4h.weight": "model-00009-of-00014.safetensors",
336
+ "transformer.h.33.post_attention_layernorm.bias": "model-00009-of-00014.safetensors",
337
+ "transformer.h.33.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
338
+ "transformer.h.33.self_attention.dense.bias": "model-00009-of-00014.safetensors",
339
+ "transformer.h.33.self_attention.dense.weight": "model-00009-of-00014.safetensors",
340
+ "transformer.h.33.self_attention.query_key_value.bias": "model-00009-of-00014.safetensors",
341
+ "transformer.h.33.self_attention.query_key_value.weight": "model-00009-of-00014.safetensors",
342
+ "transformer.h.34.input_layernorm.bias": "model-00009-of-00014.safetensors",
343
+ "transformer.h.34.input_layernorm.weight": "model-00009-of-00014.safetensors",
344
+ "transformer.h.34.mlp.dense_4h_to_h.bias": "model-00010-of-00014.safetensors",
345
+ "transformer.h.34.mlp.dense_4h_to_h.weight": "model-00010-of-00014.safetensors",
346
+ "transformer.h.34.mlp.dense_h_to_4h.bias": "model-00010-of-00014.safetensors",
347
+ "transformer.h.34.mlp.dense_h_to_4h.weight": "model-00010-of-00014.safetensors",
348
+ "transformer.h.34.post_attention_layernorm.bias": "model-00009-of-00014.safetensors",
349
+ "transformer.h.34.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
350
+ "transformer.h.34.self_attention.dense.bias": "model-00009-of-00014.safetensors",
351
+ "transformer.h.34.self_attention.dense.weight": "model-00009-of-00014.safetensors",
352
+ "transformer.h.34.self_attention.query_key_value.bias": "model-00009-of-00014.safetensors",
353
+ "transformer.h.34.self_attention.query_key_value.weight": "model-00009-of-00014.safetensors",
354
+ "transformer.h.35.input_layernorm.bias": "model-00010-of-00014.safetensors",
355
+ "transformer.h.35.input_layernorm.weight": "model-00010-of-00014.safetensors",
356
+ "transformer.h.35.mlp.dense_4h_to_h.bias": "model-00010-of-00014.safetensors",
357
+ "transformer.h.35.mlp.dense_4h_to_h.weight": "model-00010-of-00014.safetensors",
358
+ "transformer.h.35.mlp.dense_h_to_4h.bias": "model-00010-of-00014.safetensors",
359
+ "transformer.h.35.mlp.dense_h_to_4h.weight": "model-00010-of-00014.safetensors",
360
+ "transformer.h.35.post_attention_layernorm.bias": "model-00010-of-00014.safetensors",
361
+ "transformer.h.35.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
362
+ "transformer.h.35.self_attention.dense.bias": "model-00010-of-00014.safetensors",
363
+ "transformer.h.35.self_attention.dense.weight": "model-00010-of-00014.safetensors",
364
+ "transformer.h.35.self_attention.query_key_value.bias": "model-00010-of-00014.safetensors",
365
+ "transformer.h.35.self_attention.query_key_value.weight": "model-00010-of-00014.safetensors",
366
+ "transformer.h.36.input_layernorm.bias": "model-00010-of-00014.safetensors",
367
+ "transformer.h.36.input_layernorm.weight": "model-00010-of-00014.safetensors",
368
+ "transformer.h.36.mlp.dense_4h_to_h.bias": "model-00010-of-00014.safetensors",
369
+ "transformer.h.36.mlp.dense_4h_to_h.weight": "model-00010-of-00014.safetensors",
370
+ "transformer.h.36.mlp.dense_h_to_4h.bias": "model-00010-of-00014.safetensors",
371
+ "transformer.h.36.mlp.dense_h_to_4h.weight": "model-00010-of-00014.safetensors",
372
+ "transformer.h.36.post_attention_layernorm.bias": "model-00010-of-00014.safetensors",
373
+ "transformer.h.36.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
374
+ "transformer.h.36.self_attention.dense.bias": "model-00010-of-00014.safetensors",
375
+ "transformer.h.36.self_attention.dense.weight": "model-00010-of-00014.safetensors",
376
+ "transformer.h.36.self_attention.query_key_value.bias": "model-00010-of-00014.safetensors",
377
+ "transformer.h.36.self_attention.query_key_value.weight": "model-00010-of-00014.safetensors",
378
+ "transformer.h.37.input_layernorm.bias": "model-00010-of-00014.safetensors",
379
+ "transformer.h.37.input_layernorm.weight": "model-00010-of-00014.safetensors",
380
+ "transformer.h.37.mlp.dense_4h_to_h.bias": "model-00010-of-00014.safetensors",
381
+ "transformer.h.37.mlp.dense_4h_to_h.weight": "model-00010-of-00014.safetensors",
382
+ "transformer.h.37.mlp.dense_h_to_4h.bias": "model-00010-of-00014.safetensors",
383
+ "transformer.h.37.mlp.dense_h_to_4h.weight": "model-00010-of-00014.safetensors",
384
+ "transformer.h.37.post_attention_layernorm.bias": "model-00010-of-00014.safetensors",
385
+ "transformer.h.37.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
386
+ "transformer.h.37.self_attention.dense.bias": "model-00010-of-00014.safetensors",
387
+ "transformer.h.37.self_attention.dense.weight": "model-00010-of-00014.safetensors",
388
+ "transformer.h.37.self_attention.query_key_value.bias": "model-00010-of-00014.safetensors",
389
+ "transformer.h.37.self_attention.query_key_value.weight": "model-00010-of-00014.safetensors",
390
+ "transformer.h.38.input_layernorm.bias": "model-00010-of-00014.safetensors",
391
+ "transformer.h.38.input_layernorm.weight": "model-00010-of-00014.safetensors",
392
+ "transformer.h.38.mlp.dense_4h_to_h.bias": "model-00011-of-00014.safetensors",
393
+ "transformer.h.38.mlp.dense_4h_to_h.weight": "model-00011-of-00014.safetensors",
394
+ "transformer.h.38.mlp.dense_h_to_4h.bias": "model-00011-of-00014.safetensors",
395
+ "transformer.h.38.mlp.dense_h_to_4h.weight": "model-00011-of-00014.safetensors",
396
+ "transformer.h.38.post_attention_layernorm.bias": "model-00010-of-00014.safetensors",
397
+ "transformer.h.38.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
398
+ "transformer.h.38.self_attention.dense.bias": "model-00010-of-00014.safetensors",
399
+ "transformer.h.38.self_attention.dense.weight": "model-00010-of-00014.safetensors",
400
+ "transformer.h.38.self_attention.query_key_value.bias": "model-00010-of-00014.safetensors",
401
+ "transformer.h.38.self_attention.query_key_value.weight": "model-00010-of-00014.safetensors",
402
+ "transformer.h.39.input_layernorm.bias": "model-00011-of-00014.safetensors",
403
+ "transformer.h.39.input_layernorm.weight": "model-00011-of-00014.safetensors",
404
+ "transformer.h.39.mlp.dense_4h_to_h.bias": "model-00011-of-00014.safetensors",
405
+ "transformer.h.39.mlp.dense_4h_to_h.weight": "model-00011-of-00014.safetensors",
406
+ "transformer.h.39.mlp.dense_h_to_4h.bias": "model-00011-of-00014.safetensors",
407
+ "transformer.h.39.mlp.dense_h_to_4h.weight": "model-00011-of-00014.safetensors",
408
+ "transformer.h.39.post_attention_layernorm.bias": "model-00011-of-00014.safetensors",
409
+ "transformer.h.39.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
410
+ "transformer.h.39.self_attention.dense.bias": "model-00011-of-00014.safetensors",
411
+ "transformer.h.39.self_attention.dense.weight": "model-00011-of-00014.safetensors",
412
+ "transformer.h.39.self_attention.query_key_value.bias": "model-00011-of-00014.safetensors",
413
+ "transformer.h.39.self_attention.query_key_value.weight": "model-00011-of-00014.safetensors",
414
+ "transformer.h.4.input_layernorm.bias": "model-00002-of-00014.safetensors",
415
+ "transformer.h.4.input_layernorm.weight": "model-00002-of-00014.safetensors",
416
+ "transformer.h.4.mlp.dense_4h_to_h.bias": "model-00002-of-00014.safetensors",
417
+ "transformer.h.4.mlp.dense_4h_to_h.weight": "model-00002-of-00014.safetensors",
418
+ "transformer.h.4.mlp.dense_h_to_4h.bias": "model-00002-of-00014.safetensors",
419
+ "transformer.h.4.mlp.dense_h_to_4h.weight": "model-00002-of-00014.safetensors",
420
+ "transformer.h.4.post_attention_layernorm.bias": "model-00002-of-00014.safetensors",
421
+ "transformer.h.4.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
422
+ "transformer.h.4.self_attention.dense.bias": "model-00002-of-00014.safetensors",
423
+ "transformer.h.4.self_attention.dense.weight": "model-00002-of-00014.safetensors",
424
+ "transformer.h.4.self_attention.query_key_value.bias": "model-00002-of-00014.safetensors",
425
+ "transformer.h.4.self_attention.query_key_value.weight": "model-00002-of-00014.safetensors",
426
+ "transformer.h.40.input_layernorm.bias": "model-00011-of-00014.safetensors",
427
+ "transformer.h.40.input_layernorm.weight": "model-00011-of-00014.safetensors",
428
+ "transformer.h.40.mlp.dense_4h_to_h.bias": "model-00011-of-00014.safetensors",
429
+ "transformer.h.40.mlp.dense_4h_to_h.weight": "model-00011-of-00014.safetensors",
430
+ "transformer.h.40.mlp.dense_h_to_4h.bias": "model-00011-of-00014.safetensors",
431
+ "transformer.h.40.mlp.dense_h_to_4h.weight": "model-00011-of-00014.safetensors",
432
+ "transformer.h.40.post_attention_layernorm.bias": "model-00011-of-00014.safetensors",
433
+ "transformer.h.40.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
434
+ "transformer.h.40.self_attention.dense.bias": "model-00011-of-00014.safetensors",
435
+ "transformer.h.40.self_attention.dense.weight": "model-00011-of-00014.safetensors",
436
+ "transformer.h.40.self_attention.query_key_value.bias": "model-00011-of-00014.safetensors",
437
+ "transformer.h.40.self_attention.query_key_value.weight": "model-00011-of-00014.safetensors",
438
+ "transformer.h.41.input_layernorm.bias": "model-00011-of-00014.safetensors",
439
+ "transformer.h.41.input_layernorm.weight": "model-00011-of-00014.safetensors",
440
+ "transformer.h.41.mlp.dense_4h_to_h.bias": "model-00011-of-00014.safetensors",
441
+ "transformer.h.41.mlp.dense_4h_to_h.weight": "model-00011-of-00014.safetensors",
442
+ "transformer.h.41.mlp.dense_h_to_4h.bias": "model-00011-of-00014.safetensors",
443
+ "transformer.h.41.mlp.dense_h_to_4h.weight": "model-00011-of-00014.safetensors",
444
+ "transformer.h.41.post_attention_layernorm.bias": "model-00011-of-00014.safetensors",
445
+ "transformer.h.41.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
446
+ "transformer.h.41.self_attention.dense.bias": "model-00011-of-00014.safetensors",
447
+ "transformer.h.41.self_attention.dense.weight": "model-00011-of-00014.safetensors",
448
+ "transformer.h.41.self_attention.query_key_value.bias": "model-00011-of-00014.safetensors",
449
+ "transformer.h.41.self_attention.query_key_value.weight": "model-00011-of-00014.safetensors",
450
+ "transformer.h.42.input_layernorm.bias": "model-00011-of-00014.safetensors",
451
+ "transformer.h.42.input_layernorm.weight": "model-00011-of-00014.safetensors",
452
+ "transformer.h.42.mlp.dense_4h_to_h.bias": "model-00012-of-00014.safetensors",
453
+ "transformer.h.42.mlp.dense_4h_to_h.weight": "model-00012-of-00014.safetensors",
454
+ "transformer.h.42.mlp.dense_h_to_4h.bias": "model-00012-of-00014.safetensors",
455
+ "transformer.h.42.mlp.dense_h_to_4h.weight": "model-00012-of-00014.safetensors",
456
+ "transformer.h.42.post_attention_layernorm.bias": "model-00011-of-00014.safetensors",
457
+ "transformer.h.42.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
458
+ "transformer.h.42.self_attention.dense.bias": "model-00011-of-00014.safetensors",
459
+ "transformer.h.42.self_attention.dense.weight": "model-00011-of-00014.safetensors",
460
+ "transformer.h.42.self_attention.query_key_value.bias": "model-00011-of-00014.safetensors",
461
+ "transformer.h.42.self_attention.query_key_value.weight": "model-00011-of-00014.safetensors",
462
+ "transformer.h.43.input_layernorm.bias": "model-00012-of-00014.safetensors",
463
+ "transformer.h.43.input_layernorm.weight": "model-00012-of-00014.safetensors",
464
+ "transformer.h.43.mlp.dense_4h_to_h.bias": "model-00012-of-00014.safetensors",
465
+ "transformer.h.43.mlp.dense_4h_to_h.weight": "model-00012-of-00014.safetensors",
466
+ "transformer.h.43.mlp.dense_h_to_4h.bias": "model-00012-of-00014.safetensors",
467
+ "transformer.h.43.mlp.dense_h_to_4h.weight": "model-00012-of-00014.safetensors",
468
+ "transformer.h.43.post_attention_layernorm.bias": "model-00012-of-00014.safetensors",
469
+ "transformer.h.43.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
470
+ "transformer.h.43.self_attention.dense.bias": "model-00012-of-00014.safetensors",
471
+ "transformer.h.43.self_attention.dense.weight": "model-00012-of-00014.safetensors",
472
+ "transformer.h.43.self_attention.query_key_value.bias": "model-00012-of-00014.safetensors",
473
+ "transformer.h.43.self_attention.query_key_value.weight": "model-00012-of-00014.safetensors",
474
+ "transformer.h.44.input_layernorm.bias": "model-00012-of-00014.safetensors",
475
+ "transformer.h.44.input_layernorm.weight": "model-00012-of-00014.safetensors",
476
+ "transformer.h.44.mlp.dense_4h_to_h.bias": "model-00012-of-00014.safetensors",
477
+ "transformer.h.44.mlp.dense_4h_to_h.weight": "model-00012-of-00014.safetensors",
478
+ "transformer.h.44.mlp.dense_h_to_4h.bias": "model-00012-of-00014.safetensors",
479
+ "transformer.h.44.mlp.dense_h_to_4h.weight": "model-00012-of-00014.safetensors",
480
+ "transformer.h.44.post_attention_layernorm.bias": "model-00012-of-00014.safetensors",
481
+ "transformer.h.44.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
482
+ "transformer.h.44.self_attention.dense.bias": "model-00012-of-00014.safetensors",
483
+ "transformer.h.44.self_attention.dense.weight": "model-00012-of-00014.safetensors",
484
+ "transformer.h.44.self_attention.query_key_value.bias": "model-00012-of-00014.safetensors",
485
+ "transformer.h.44.self_attention.query_key_value.weight": "model-00012-of-00014.safetensors",
486
+ "transformer.h.45.input_layernorm.bias": "model-00012-of-00014.safetensors",
487
+ "transformer.h.45.input_layernorm.weight": "model-00012-of-00014.safetensors",
488
+ "transformer.h.45.mlp.dense_4h_to_h.bias": "model-00012-of-00014.safetensors",
489
+ "transformer.h.45.mlp.dense_4h_to_h.weight": "model-00012-of-00014.safetensors",
490
+ "transformer.h.45.mlp.dense_h_to_4h.bias": "model-00012-of-00014.safetensors",
491
+ "transformer.h.45.mlp.dense_h_to_4h.weight": "model-00012-of-00014.safetensors",
492
+ "transformer.h.45.post_attention_layernorm.bias": "model-00012-of-00014.safetensors",
493
+ "transformer.h.45.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
494
+ "transformer.h.45.self_attention.dense.bias": "model-00012-of-00014.safetensors",
495
+ "transformer.h.45.self_attention.dense.weight": "model-00012-of-00014.safetensors",
496
+ "transformer.h.45.self_attention.query_key_value.bias": "model-00012-of-00014.safetensors",
497
+ "transformer.h.45.self_attention.query_key_value.weight": "model-00012-of-00014.safetensors",
498
+ "transformer.h.46.input_layernorm.bias": "model-00012-of-00014.safetensors",
499
+ "transformer.h.46.input_layernorm.weight": "model-00012-of-00014.safetensors",
500
+ "transformer.h.46.mlp.dense_4h_to_h.bias": "model-00013-of-00014.safetensors",
501
+ "transformer.h.46.mlp.dense_4h_to_h.weight": "model-00013-of-00014.safetensors",
502
+ "transformer.h.46.mlp.dense_h_to_4h.bias": "model-00013-of-00014.safetensors",
503
+ "transformer.h.46.mlp.dense_h_to_4h.weight": "model-00013-of-00014.safetensors",
504
+ "transformer.h.46.post_attention_layernorm.bias": "model-00012-of-00014.safetensors",
505
+ "transformer.h.46.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
506
+ "transformer.h.46.self_attention.dense.bias": "model-00012-of-00014.safetensors",
507
+ "transformer.h.46.self_attention.dense.weight": "model-00012-of-00014.safetensors",
508
+ "transformer.h.46.self_attention.query_key_value.bias": "model-00012-of-00014.safetensors",
509
+ "transformer.h.46.self_attention.query_key_value.weight": "model-00012-of-00014.safetensors",
510
+ "transformer.h.47.input_layernorm.bias": "model-00013-of-00014.safetensors",
511
+ "transformer.h.47.input_layernorm.weight": "model-00013-of-00014.safetensors",
512
+ "transformer.h.47.mlp.dense_4h_to_h.bias": "model-00013-of-00014.safetensors",
513
+ "transformer.h.47.mlp.dense_4h_to_h.weight": "model-00013-of-00014.safetensors",
514
+ "transformer.h.47.mlp.dense_h_to_4h.bias": "model-00013-of-00014.safetensors",
515
+ "transformer.h.47.mlp.dense_h_to_4h.weight": "model-00013-of-00014.safetensors",
516
+ "transformer.h.47.post_attention_layernorm.bias": "model-00013-of-00014.safetensors",
517
+ "transformer.h.47.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
518
+ "transformer.h.47.self_attention.dense.bias": "model-00013-of-00014.safetensors",
519
+ "transformer.h.47.self_attention.dense.weight": "model-00013-of-00014.safetensors",
520
+ "transformer.h.47.self_attention.query_key_value.bias": "model-00013-of-00014.safetensors",
521
+ "transformer.h.47.self_attention.query_key_value.weight": "model-00013-of-00014.safetensors",
522
+ "transformer.h.48.input_layernorm.bias": "model-00013-of-00014.safetensors",
523
+ "transformer.h.48.input_layernorm.weight": "model-00013-of-00014.safetensors",
524
+ "transformer.h.48.mlp.dense_4h_to_h.bias": "model-00013-of-00014.safetensors",
525
+ "transformer.h.48.mlp.dense_4h_to_h.weight": "model-00013-of-00014.safetensors",
526
+ "transformer.h.48.mlp.dense_h_to_4h.bias": "model-00013-of-00014.safetensors",
527
+ "transformer.h.48.mlp.dense_h_to_4h.weight": "model-00013-of-00014.safetensors",
528
+ "transformer.h.48.post_attention_layernorm.bias": "model-00013-of-00014.safetensors",
529
+ "transformer.h.48.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
530
+ "transformer.h.48.self_attention.dense.bias": "model-00013-of-00014.safetensors",
531
+ "transformer.h.48.self_attention.dense.weight": "model-00013-of-00014.safetensors",
532
+ "transformer.h.48.self_attention.query_key_value.bias": "model-00013-of-00014.safetensors",
533
+ "transformer.h.48.self_attention.query_key_value.weight": "model-00013-of-00014.safetensors",
534
+ "transformer.h.49.input_layernorm.bias": "model-00013-of-00014.safetensors",
535
+ "transformer.h.49.input_layernorm.weight": "model-00013-of-00014.safetensors",
536
+ "transformer.h.49.mlp.dense_4h_to_h.bias": "model-00013-of-00014.safetensors",
537
+ "transformer.h.49.mlp.dense_4h_to_h.weight": "model-00013-of-00014.safetensors",
538
+ "transformer.h.49.mlp.dense_h_to_4h.bias": "model-00013-of-00014.safetensors",
539
+ "transformer.h.49.mlp.dense_h_to_4h.weight": "model-00013-of-00014.safetensors",
540
+ "transformer.h.49.post_attention_layernorm.bias": "model-00013-of-00014.safetensors",
541
+ "transformer.h.49.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
542
+ "transformer.h.49.self_attention.dense.bias": "model-00013-of-00014.safetensors",
543
+ "transformer.h.49.self_attention.dense.weight": "model-00013-of-00014.safetensors",
544
+ "transformer.h.49.self_attention.query_key_value.bias": "model-00013-of-00014.safetensors",
545
+ "transformer.h.49.self_attention.query_key_value.weight": "model-00013-of-00014.safetensors",
546
+ "transformer.h.5.input_layernorm.bias": "model-00002-of-00014.safetensors",
547
+ "transformer.h.5.input_layernorm.weight": "model-00002-of-00014.safetensors",
548
+ "transformer.h.5.mlp.dense_4h_to_h.bias": "model-00002-of-00014.safetensors",
549
+ "transformer.h.5.mlp.dense_4h_to_h.weight": "model-00002-of-00014.safetensors",
550
+ "transformer.h.5.mlp.dense_h_to_4h.bias": "model-00002-of-00014.safetensors",
551
+ "transformer.h.5.mlp.dense_h_to_4h.weight": "model-00002-of-00014.safetensors",
552
+ "transformer.h.5.post_attention_layernorm.bias": "model-00002-of-00014.safetensors",
553
+ "transformer.h.5.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
554
+ "transformer.h.5.self_attention.dense.bias": "model-00002-of-00014.safetensors",
555
+ "transformer.h.5.self_attention.dense.weight": "model-00002-of-00014.safetensors",
556
+ "transformer.h.5.self_attention.query_key_value.bias": "model-00002-of-00014.safetensors",
557
+ "transformer.h.5.self_attention.query_key_value.weight": "model-00002-of-00014.safetensors",
558
+ "transformer.h.50.input_layernorm.bias": "model-00013-of-00014.safetensors",
559
+ "transformer.h.50.input_layernorm.weight": "model-00013-of-00014.safetensors",
560
+ "transformer.h.50.mlp.dense_4h_to_h.bias": "model-00014-of-00014.safetensors",
561
+ "transformer.h.50.mlp.dense_4h_to_h.weight": "model-00014-of-00014.safetensors",
562
+ "transformer.h.50.mlp.dense_h_to_4h.bias": "model-00014-of-00014.safetensors",
563
+ "transformer.h.50.mlp.dense_h_to_4h.weight": "model-00014-of-00014.safetensors",
564
+ "transformer.h.50.post_attention_layernorm.bias": "model-00013-of-00014.safetensors",
565
+ "transformer.h.50.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
566
+ "transformer.h.50.self_attention.dense.bias": "model-00013-of-00014.safetensors",
567
+ "transformer.h.50.self_attention.dense.weight": "model-00013-of-00014.safetensors",
568
+ "transformer.h.50.self_attention.query_key_value.bias": "model-00013-of-00014.safetensors",
569
+ "transformer.h.50.self_attention.query_key_value.weight": "model-00013-of-00014.safetensors",
570
+ "transformer.h.51.input_layernorm.bias": "model-00014-of-00014.safetensors",
571
+ "transformer.h.51.input_layernorm.weight": "model-00014-of-00014.safetensors",
572
+ "transformer.h.51.mlp.dense_4h_to_h.bias": "model-00014-of-00014.safetensors",
573
+ "transformer.h.51.mlp.dense_4h_to_h.weight": "model-00014-of-00014.safetensors",
574
+ "transformer.h.51.mlp.dense_h_to_4h.bias": "model-00014-of-00014.safetensors",
575
+ "transformer.h.51.mlp.dense_h_to_4h.weight": "model-00014-of-00014.safetensors",
576
+ "transformer.h.51.post_attention_layernorm.bias": "model-00014-of-00014.safetensors",
577
+ "transformer.h.51.post_attention_layernorm.weight": "model-00014-of-00014.safetensors",
578
+ "transformer.h.51.self_attention.dense.bias": "model-00014-of-00014.safetensors",
579
+ "transformer.h.51.self_attention.dense.weight": "model-00014-of-00014.safetensors",
580
+ "transformer.h.51.self_attention.query_key_value.bias": "model-00014-of-00014.safetensors",
581
+ "transformer.h.51.self_attention.query_key_value.weight": "model-00014-of-00014.safetensors",
582
+ "transformer.h.52.input_layernorm.bias": "model-00014-of-00014.safetensors",
583
+ "transformer.h.52.input_layernorm.weight": "model-00014-of-00014.safetensors",
584
+ "transformer.h.52.mlp.dense_4h_to_h.bias": "model-00014-of-00014.safetensors",
585
+ "transformer.h.52.mlp.dense_4h_to_h.weight": "model-00014-of-00014.safetensors",
586
+ "transformer.h.52.mlp.dense_h_to_4h.bias": "model-00014-of-00014.safetensors",
587
+ "transformer.h.52.mlp.dense_h_to_4h.weight": "model-00014-of-00014.safetensors",
588
+ "transformer.h.52.post_attention_layernorm.bias": "model-00014-of-00014.safetensors",
589
+ "transformer.h.52.post_attention_layernorm.weight": "model-00014-of-00014.safetensors",
590
+ "transformer.h.52.self_attention.dense.bias": "model-00014-of-00014.safetensors",
591
+ "transformer.h.52.self_attention.dense.weight": "model-00014-of-00014.safetensors",
592
+ "transformer.h.52.self_attention.query_key_value.bias": "model-00014-of-00014.safetensors",
593
+ "transformer.h.52.self_attention.query_key_value.weight": "model-00014-of-00014.safetensors",
594
+ "transformer.h.53.input_layernorm.bias": "model-00014-of-00014.safetensors",
595
+ "transformer.h.53.input_layernorm.weight": "model-00014-of-00014.safetensors",
596
+ "transformer.h.53.mlp.dense_4h_to_h.bias": "model-00014-of-00014.safetensors",
597
+ "transformer.h.53.mlp.dense_4h_to_h.weight": "model-00014-of-00014.safetensors",
598
+ "transformer.h.53.mlp.dense_h_to_4h.bias": "model-00014-of-00014.safetensors",
599
+ "transformer.h.53.mlp.dense_h_to_4h.weight": "model-00014-of-00014.safetensors",
600
+ "transformer.h.53.post_attention_layernorm.bias": "model-00014-of-00014.safetensors",
601
+ "transformer.h.53.post_attention_layernorm.weight": "model-00014-of-00014.safetensors",
602
+ "transformer.h.53.self_attention.dense.bias": "model-00014-of-00014.safetensors",
603
+ "transformer.h.53.self_attention.dense.weight": "model-00014-of-00014.safetensors",
604
+ "transformer.h.53.self_attention.query_key_value.bias": "model-00014-of-00014.safetensors",
605
+ "transformer.h.53.self_attention.query_key_value.weight": "model-00014-of-00014.safetensors",
606
+ "transformer.h.6.input_layernorm.bias": "model-00002-of-00014.safetensors",
607
+ "transformer.h.6.input_layernorm.weight": "model-00002-of-00014.safetensors",
608
+ "transformer.h.6.mlp.dense_4h_to_h.bias": "model-00003-of-00014.safetensors",
609
+ "transformer.h.6.mlp.dense_4h_to_h.weight": "model-00003-of-00014.safetensors",
610
+ "transformer.h.6.mlp.dense_h_to_4h.bias": "model-00003-of-00014.safetensors",
611
+ "transformer.h.6.mlp.dense_h_to_4h.weight": "model-00003-of-00014.safetensors",
612
+ "transformer.h.6.post_attention_layernorm.bias": "model-00002-of-00014.safetensors",
613
+ "transformer.h.6.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
614
+ "transformer.h.6.self_attention.dense.bias": "model-00002-of-00014.safetensors",
615
+ "transformer.h.6.self_attention.dense.weight": "model-00002-of-00014.safetensors",
616
+ "transformer.h.6.self_attention.query_key_value.bias": "model-00002-of-00014.safetensors",
617
+ "transformer.h.6.self_attention.query_key_value.weight": "model-00002-of-00014.safetensors",
618
+ "transformer.h.7.input_layernorm.bias": "model-00003-of-00014.safetensors",
619
+ "transformer.h.7.input_layernorm.weight": "model-00003-of-00014.safetensors",
620
+ "transformer.h.7.mlp.dense_4h_to_h.bias": "model-00003-of-00014.safetensors",
621
+ "transformer.h.7.mlp.dense_4h_to_h.weight": "model-00003-of-00014.safetensors",
622
+ "transformer.h.7.mlp.dense_h_to_4h.bias": "model-00003-of-00014.safetensors",
623
+ "transformer.h.7.mlp.dense_h_to_4h.weight": "model-00003-of-00014.safetensors",
624
+ "transformer.h.7.post_attention_layernorm.bias": "model-00003-of-00014.safetensors",
625
+ "transformer.h.7.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
626
+ "transformer.h.7.self_attention.dense.bias": "model-00003-of-00014.safetensors",
627
+ "transformer.h.7.self_attention.dense.weight": "model-00003-of-00014.safetensors",
628
+ "transformer.h.7.self_attention.query_key_value.bias": "model-00003-of-00014.safetensors",
629
+ "transformer.h.7.self_attention.query_key_value.weight": "model-00003-of-00014.safetensors",
630
+ "transformer.h.8.input_layernorm.bias": "model-00003-of-00014.safetensors",
631
+ "transformer.h.8.input_layernorm.weight": "model-00003-of-00014.safetensors",
632
+ "transformer.h.8.mlp.dense_4h_to_h.bias": "model-00003-of-00014.safetensors",
633
+ "transformer.h.8.mlp.dense_4h_to_h.weight": "model-00003-of-00014.safetensors",
634
+ "transformer.h.8.mlp.dense_h_to_4h.bias": "model-00003-of-00014.safetensors",
635
+ "transformer.h.8.mlp.dense_h_to_4h.weight": "model-00003-of-00014.safetensors",
636
+ "transformer.h.8.post_attention_layernorm.bias": "model-00003-of-00014.safetensors",
637
+ "transformer.h.8.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
638
+ "transformer.h.8.self_attention.dense.bias": "model-00003-of-00014.safetensors",
639
+ "transformer.h.8.self_attention.dense.weight": "model-00003-of-00014.safetensors",
640
+ "transformer.h.8.self_attention.query_key_value.bias": "model-00003-of-00014.safetensors",
641
+ "transformer.h.8.self_attention.query_key_value.weight": "model-00003-of-00014.safetensors",
642
+ "transformer.h.9.input_layernorm.bias": "model-00003-of-00014.safetensors",
643
+ "transformer.h.9.input_layernorm.weight": "model-00003-of-00014.safetensors",
644
+ "transformer.h.9.mlp.dense_4h_to_h.bias": "model-00003-of-00014.safetensors",
645
+ "transformer.h.9.mlp.dense_4h_to_h.weight": "model-00003-of-00014.safetensors",
646
+ "transformer.h.9.mlp.dense_h_to_4h.bias": "model-00003-of-00014.safetensors",
647
+ "transformer.h.9.mlp.dense_h_to_4h.weight": "model-00003-of-00014.safetensors",
648
+ "transformer.h.9.post_attention_layernorm.bias": "model-00003-of-00014.safetensors",
649
+ "transformer.h.9.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
650
+ "transformer.h.9.self_attention.dense.bias": "model-00003-of-00014.safetensors",
651
+ "transformer.h.9.self_attention.dense.weight": "model-00003-of-00014.safetensors",
652
+ "transformer.h.9.self_attention.query_key_value.bias": "model-00003-of-00014.safetensors",
653
+ "transformer.h.9.self_attention.query_key_value.weight": "model-00003-of-00014.safetensors",
654
+ "transformer.ln_f.bias": "model-00014-of-00014.safetensors",
655
+ "transformer.ln_f.weight": "model-00014-of-00014.safetensors",
656
+ "transformer.word_embeddings.weight": "model-00001-of-00014.safetensors",
657
+ "transformer.word_embeddings_layernorm.bias": "model-00001-of-00014.safetensors",
658
+ "transformer.word_embeddings_layernorm.weight": "model-00001-of-00014.safetensors"
659
+ }
660
+ }
pytorch_model-00005-of-00007.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:3b403b4d68f9c8ae70a8ea4f79da29b9d3d356473e60c3c42883bef8d0624e28
3
- size 9866528411
 
 
 
 
pytorch_model-00006-of-00007.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:48a1fa998cfe7ea43ae6723ab19558ea923e23f60ed6e49619f9919728ed53f3
3
- size 9866528411
 
 
 
 
pytorch_model-00007-of-00007.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:be5400fd439c68606aa90d1b658c22314a0f72abad38e197d397a99f2ee444fe
3
- size 9455398375
 
 
 
 
pytorch_model.bin.index.json DELETED
@@ -1,661 +0,0 @@
1
- {
2
- "metadata": {
3
- "total_size": 68433899520
4
- },
5
- "weight_map": {
6
- "lm_head.weight": "pytorch_model-00001-of-00007.bin",
7
- "transformer.h.0.input_layernorm.bias": "pytorch_model-00001-of-00007.bin",
8
- "transformer.h.0.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
9
- "transformer.h.0.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00007.bin",
10
- "transformer.h.0.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00007.bin",
11
- "transformer.h.0.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00007.bin",
12
- "transformer.h.0.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00007.bin",
13
- "transformer.h.0.post_attention_layernorm.bias": "pytorch_model-00001-of-00007.bin",
14
- "transformer.h.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
15
- "transformer.h.0.self_attention.dense.bias": "pytorch_model-00001-of-00007.bin",
16
- "transformer.h.0.self_attention.dense.weight": "pytorch_model-00001-of-00007.bin",
17
- "transformer.h.0.self_attention.query_key_value.bias": "pytorch_model-00001-of-00007.bin",
18
- "transformer.h.0.self_attention.query_key_value.weight": "pytorch_model-00001-of-00007.bin",
19
- "transformer.h.1.input_layernorm.bias": "pytorch_model-00001-of-00007.bin",
20
- "transformer.h.1.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
21
- "transformer.h.1.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00007.bin",
22
- "transformer.h.1.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00007.bin",
23
- "transformer.h.1.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00007.bin",
24
- "transformer.h.1.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00007.bin",
25
- "transformer.h.1.post_attention_layernorm.bias": "pytorch_model-00001-of-00007.bin",
26
- "transformer.h.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
27
- "transformer.h.1.self_attention.dense.bias": "pytorch_model-00001-of-00007.bin",
28
- "transformer.h.1.self_attention.dense.weight": "pytorch_model-00001-of-00007.bin",
29
- "transformer.h.1.self_attention.query_key_value.bias": "pytorch_model-00001-of-00007.bin",
30
- "transformer.h.1.self_attention.query_key_value.weight": "pytorch_model-00001-of-00007.bin",
31
- "transformer.h.10.input_layernorm.bias": "pytorch_model-00002-of-00007.bin",
32
- "transformer.h.10.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
33
- "transformer.h.10.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00007.bin",
34
- "transformer.h.10.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00007.bin",
35
- "transformer.h.10.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00007.bin",
36
- "transformer.h.10.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00007.bin",
37
- "transformer.h.10.post_attention_layernorm.bias": "pytorch_model-00002-of-00007.bin",
38
- "transformer.h.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
39
- "transformer.h.10.self_attention.dense.bias": "pytorch_model-00002-of-00007.bin",
40
- "transformer.h.10.self_attention.dense.weight": "pytorch_model-00002-of-00007.bin",
41
- "transformer.h.10.self_attention.query_key_value.bias": "pytorch_model-00002-of-00007.bin",
42
- "transformer.h.10.self_attention.query_key_value.weight": "pytorch_model-00002-of-00007.bin",
43
- "transformer.h.11.input_layernorm.bias": "pytorch_model-00002-of-00007.bin",
44
- "transformer.h.11.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
45
- "transformer.h.11.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00007.bin",
46
- "transformer.h.11.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00007.bin",
47
- "transformer.h.11.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00007.bin",
48
- "transformer.h.11.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00007.bin",
49
- "transformer.h.11.post_attention_layernorm.bias": "pytorch_model-00002-of-00007.bin",
50
- "transformer.h.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
51
- "transformer.h.11.self_attention.dense.bias": "pytorch_model-00002-of-00007.bin",
52
- "transformer.h.11.self_attention.dense.weight": "pytorch_model-00002-of-00007.bin",
53
- "transformer.h.11.self_attention.query_key_value.bias": "pytorch_model-00002-of-00007.bin",
54
- "transformer.h.11.self_attention.query_key_value.weight": "pytorch_model-00002-of-00007.bin",
55
- "transformer.h.12.input_layernorm.bias": "pytorch_model-00002-of-00007.bin",
56
- "transformer.h.12.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
57
- "transformer.h.12.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00007.bin",
58
- "transformer.h.12.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00007.bin",
59
- "transformer.h.12.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00007.bin",
60
- "transformer.h.12.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00007.bin",
61
- "transformer.h.12.post_attention_layernorm.bias": "pytorch_model-00002-of-00007.bin",
62
- "transformer.h.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
63
- "transformer.h.12.self_attention.dense.bias": "pytorch_model-00002-of-00007.bin",
64
- "transformer.h.12.self_attention.dense.weight": "pytorch_model-00002-of-00007.bin",
65
- "transformer.h.12.self_attention.query_key_value.bias": "pytorch_model-00002-of-00007.bin",
66
- "transformer.h.12.self_attention.query_key_value.weight": "pytorch_model-00002-of-00007.bin",
67
- "transformer.h.13.input_layernorm.bias": "pytorch_model-00002-of-00007.bin",
68
- "transformer.h.13.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
69
- "transformer.h.13.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00007.bin",
70
- "transformer.h.13.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00007.bin",
71
- "transformer.h.13.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00007.bin",
72
- "transformer.h.13.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00007.bin",
73
- "transformer.h.13.post_attention_layernorm.bias": "pytorch_model-00002-of-00007.bin",
74
- "transformer.h.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
75
- "transformer.h.13.self_attention.dense.bias": "pytorch_model-00002-of-00007.bin",
76
- "transformer.h.13.self_attention.dense.weight": "pytorch_model-00002-of-00007.bin",
77
- "transformer.h.13.self_attention.query_key_value.bias": "pytorch_model-00002-of-00007.bin",
78
- "transformer.h.13.self_attention.query_key_value.weight": "pytorch_model-00002-of-00007.bin",
79
- "transformer.h.14.input_layernorm.bias": "pytorch_model-00002-of-00007.bin",
80
- "transformer.h.14.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
81
- "transformer.h.14.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00007.bin",
82
- "transformer.h.14.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00007.bin",
83
- "transformer.h.14.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00007.bin",
84
- "transformer.h.14.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00007.bin",
85
- "transformer.h.14.post_attention_layernorm.bias": "pytorch_model-00002-of-00007.bin",
86
- "transformer.h.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
87
- "transformer.h.14.self_attention.dense.bias": "pytorch_model-00002-of-00007.bin",
88
- "transformer.h.14.self_attention.dense.weight": "pytorch_model-00002-of-00007.bin",
89
- "transformer.h.14.self_attention.query_key_value.bias": "pytorch_model-00002-of-00007.bin",
90
- "transformer.h.14.self_attention.query_key_value.weight": "pytorch_model-00002-of-00007.bin",
91
- "transformer.h.15.input_layernorm.bias": "pytorch_model-00003-of-00007.bin",
92
- "transformer.h.15.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
93
- "transformer.h.15.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00007.bin",
94
- "transformer.h.15.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00007.bin",
95
- "transformer.h.15.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00007.bin",
96
- "transformer.h.15.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00007.bin",
97
- "transformer.h.15.post_attention_layernorm.bias": "pytorch_model-00003-of-00007.bin",
98
- "transformer.h.15.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
99
- "transformer.h.15.self_attention.dense.bias": "pytorch_model-00003-of-00007.bin",
100
- "transformer.h.15.self_attention.dense.weight": "pytorch_model-00003-of-00007.bin",
101
- "transformer.h.15.self_attention.query_key_value.bias": "pytorch_model-00003-of-00007.bin",
102
- "transformer.h.15.self_attention.query_key_value.weight": "pytorch_model-00003-of-00007.bin",
103
- "transformer.h.16.input_layernorm.bias": "pytorch_model-00003-of-00007.bin",
104
- "transformer.h.16.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
105
- "transformer.h.16.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00007.bin",
106
- "transformer.h.16.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00007.bin",
107
- "transformer.h.16.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00007.bin",
108
- "transformer.h.16.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00007.bin",
109
- "transformer.h.16.post_attention_layernorm.bias": "pytorch_model-00003-of-00007.bin",
110
- "transformer.h.16.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
111
- "transformer.h.16.self_attention.dense.bias": "pytorch_model-00003-of-00007.bin",
112
- "transformer.h.16.self_attention.dense.weight": "pytorch_model-00003-of-00007.bin",
113
- "transformer.h.16.self_attention.query_key_value.bias": "pytorch_model-00003-of-00007.bin",
114
- "transformer.h.16.self_attention.query_key_value.weight": "pytorch_model-00003-of-00007.bin",
115
- "transformer.h.17.input_layernorm.bias": "pytorch_model-00003-of-00007.bin",
116
- "transformer.h.17.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
117
- "transformer.h.17.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00007.bin",
118
- "transformer.h.17.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00007.bin",
119
- "transformer.h.17.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00007.bin",
120
- "transformer.h.17.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00007.bin",
121
- "transformer.h.17.post_attention_layernorm.bias": "pytorch_model-00003-of-00007.bin",
122
- "transformer.h.17.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
123
- "transformer.h.17.self_attention.dense.bias": "pytorch_model-00003-of-00007.bin",
124
- "transformer.h.17.self_attention.dense.weight": "pytorch_model-00003-of-00007.bin",
125
- "transformer.h.17.self_attention.query_key_value.bias": "pytorch_model-00003-of-00007.bin",
126
- "transformer.h.17.self_attention.query_key_value.weight": "pytorch_model-00003-of-00007.bin",
127
- "transformer.h.18.input_layernorm.bias": "pytorch_model-00003-of-00007.bin",
128
- "transformer.h.18.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
129
- "transformer.h.18.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00007.bin",
130
- "transformer.h.18.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00007.bin",
131
- "transformer.h.18.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00007.bin",
132
- "transformer.h.18.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00007.bin",
133
- "transformer.h.18.post_attention_layernorm.bias": "pytorch_model-00003-of-00007.bin",
134
- "transformer.h.18.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
135
- "transformer.h.18.self_attention.dense.bias": "pytorch_model-00003-of-00007.bin",
136
- "transformer.h.18.self_attention.dense.weight": "pytorch_model-00003-of-00007.bin",
137
- "transformer.h.18.self_attention.query_key_value.bias": "pytorch_model-00003-of-00007.bin",
138
- "transformer.h.18.self_attention.query_key_value.weight": "pytorch_model-00003-of-00007.bin",
139
- "transformer.h.19.input_layernorm.bias": "pytorch_model-00003-of-00007.bin",
140
- "transformer.h.19.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
141
- "transformer.h.19.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00007.bin",
142
- "transformer.h.19.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00007.bin",
143
- "transformer.h.19.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00007.bin",
144
- "transformer.h.19.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00007.bin",
145
- "transformer.h.19.post_attention_layernorm.bias": "pytorch_model-00003-of-00007.bin",
146
- "transformer.h.19.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
147
- "transformer.h.19.self_attention.dense.bias": "pytorch_model-00003-of-00007.bin",
148
- "transformer.h.19.self_attention.dense.weight": "pytorch_model-00003-of-00007.bin",
149
- "transformer.h.19.self_attention.query_key_value.bias": "pytorch_model-00003-of-00007.bin",
150
- "transformer.h.19.self_attention.query_key_value.weight": "pytorch_model-00003-of-00007.bin",
151
- "transformer.h.2.input_layernorm.bias": "pytorch_model-00001-of-00007.bin",
152
- "transformer.h.2.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
153
- "transformer.h.2.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00007.bin",
154
- "transformer.h.2.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00007.bin",
155
- "transformer.h.2.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00007.bin",
156
- "transformer.h.2.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00007.bin",
157
- "transformer.h.2.post_attention_layernorm.bias": "pytorch_model-00001-of-00007.bin",
158
- "transformer.h.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
159
- "transformer.h.2.self_attention.dense.bias": "pytorch_model-00001-of-00007.bin",
160
- "transformer.h.2.self_attention.dense.weight": "pytorch_model-00001-of-00007.bin",
161
- "transformer.h.2.self_attention.query_key_value.bias": "pytorch_model-00001-of-00007.bin",
162
- "transformer.h.2.self_attention.query_key_value.weight": "pytorch_model-00001-of-00007.bin",
163
- "transformer.h.20.input_layernorm.bias": "pytorch_model-00003-of-00007.bin",
164
- "transformer.h.20.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
165
- "transformer.h.20.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00007.bin",
166
- "transformer.h.20.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00007.bin",
167
- "transformer.h.20.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00007.bin",
168
- "transformer.h.20.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00007.bin",
169
- "transformer.h.20.post_attention_layernorm.bias": "pytorch_model-00003-of-00007.bin",
170
- "transformer.h.20.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
171
- "transformer.h.20.self_attention.dense.bias": "pytorch_model-00003-of-00007.bin",
172
- "transformer.h.20.self_attention.dense.weight": "pytorch_model-00003-of-00007.bin",
173
- "transformer.h.20.self_attention.query_key_value.bias": "pytorch_model-00003-of-00007.bin",
174
- "transformer.h.20.self_attention.query_key_value.weight": "pytorch_model-00003-of-00007.bin",
175
- "transformer.h.21.input_layernorm.bias": "pytorch_model-00003-of-00007.bin",
176
- "transformer.h.21.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
177
- "transformer.h.21.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00007.bin",
178
- "transformer.h.21.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00007.bin",
179
- "transformer.h.21.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00007.bin",
180
- "transformer.h.21.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00007.bin",
181
- "transformer.h.21.post_attention_layernorm.bias": "pytorch_model-00003-of-00007.bin",
182
- "transformer.h.21.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
183
- "transformer.h.21.self_attention.dense.bias": "pytorch_model-00003-of-00007.bin",
184
- "transformer.h.21.self_attention.dense.weight": "pytorch_model-00003-of-00007.bin",
185
- "transformer.h.21.self_attention.query_key_value.bias": "pytorch_model-00003-of-00007.bin",
186
- "transformer.h.21.self_attention.query_key_value.weight": "pytorch_model-00003-of-00007.bin",
187
- "transformer.h.22.input_layernorm.bias": "pytorch_model-00003-of-00007.bin",
188
- "transformer.h.22.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
189
- "transformer.h.22.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00007.bin",
190
- "transformer.h.22.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00007.bin",
191
- "transformer.h.22.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00007.bin",
192
- "transformer.h.22.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00007.bin",
193
- "transformer.h.22.post_attention_layernorm.bias": "pytorch_model-00003-of-00007.bin",
194
- "transformer.h.22.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
195
- "transformer.h.22.self_attention.dense.bias": "pytorch_model-00003-of-00007.bin",
196
- "transformer.h.22.self_attention.dense.weight": "pytorch_model-00003-of-00007.bin",
197
- "transformer.h.22.self_attention.query_key_value.bias": "pytorch_model-00003-of-00007.bin",
198
- "transformer.h.22.self_attention.query_key_value.weight": "pytorch_model-00003-of-00007.bin",
199
- "transformer.h.23.input_layernorm.bias": "pytorch_model-00004-of-00007.bin",
200
- "transformer.h.23.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
201
- "transformer.h.23.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00007.bin",
202
- "transformer.h.23.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00007.bin",
203
- "transformer.h.23.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00007.bin",
204
- "transformer.h.23.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00007.bin",
205
- "transformer.h.23.post_attention_layernorm.bias": "pytorch_model-00004-of-00007.bin",
206
- "transformer.h.23.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
207
- "transformer.h.23.self_attention.dense.bias": "pytorch_model-00004-of-00007.bin",
208
- "transformer.h.23.self_attention.dense.weight": "pytorch_model-00004-of-00007.bin",
209
- "transformer.h.23.self_attention.query_key_value.bias": "pytorch_model-00004-of-00007.bin",
210
- "transformer.h.23.self_attention.query_key_value.weight": "pytorch_model-00004-of-00007.bin",
211
- "transformer.h.24.input_layernorm.bias": "pytorch_model-00004-of-00007.bin",
212
- "transformer.h.24.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
213
- "transformer.h.24.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00007.bin",
214
- "transformer.h.24.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00007.bin",
215
- "transformer.h.24.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00007.bin",
216
- "transformer.h.24.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00007.bin",
217
- "transformer.h.24.post_attention_layernorm.bias": "pytorch_model-00004-of-00007.bin",
218
- "transformer.h.24.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
219
- "transformer.h.24.self_attention.dense.bias": "pytorch_model-00004-of-00007.bin",
220
- "transformer.h.24.self_attention.dense.weight": "pytorch_model-00004-of-00007.bin",
221
- "transformer.h.24.self_attention.query_key_value.bias": "pytorch_model-00004-of-00007.bin",
222
- "transformer.h.24.self_attention.query_key_value.weight": "pytorch_model-00004-of-00007.bin",
223
- "transformer.h.25.input_layernorm.bias": "pytorch_model-00004-of-00007.bin",
224
- "transformer.h.25.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
225
- "transformer.h.25.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00007.bin",
226
- "transformer.h.25.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00007.bin",
227
- "transformer.h.25.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00007.bin",
228
- "transformer.h.25.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00007.bin",
229
- "transformer.h.25.post_attention_layernorm.bias": "pytorch_model-00004-of-00007.bin",
230
- "transformer.h.25.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
231
- "transformer.h.25.self_attention.dense.bias": "pytorch_model-00004-of-00007.bin",
232
- "transformer.h.25.self_attention.dense.weight": "pytorch_model-00004-of-00007.bin",
233
- "transformer.h.25.self_attention.query_key_value.bias": "pytorch_model-00004-of-00007.bin",
234
- "transformer.h.25.self_attention.query_key_value.weight": "pytorch_model-00004-of-00007.bin",
235
- "transformer.h.26.input_layernorm.bias": "pytorch_model-00004-of-00007.bin",
236
- "transformer.h.26.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
237
- "transformer.h.26.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00007.bin",
238
- "transformer.h.26.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00007.bin",
239
- "transformer.h.26.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00007.bin",
240
- "transformer.h.26.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00007.bin",
241
- "transformer.h.26.post_attention_layernorm.bias": "pytorch_model-00004-of-00007.bin",
242
- "transformer.h.26.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
243
- "transformer.h.26.self_attention.dense.bias": "pytorch_model-00004-of-00007.bin",
244
- "transformer.h.26.self_attention.dense.weight": "pytorch_model-00004-of-00007.bin",
245
- "transformer.h.26.self_attention.query_key_value.bias": "pytorch_model-00004-of-00007.bin",
246
- "transformer.h.26.self_attention.query_key_value.weight": "pytorch_model-00004-of-00007.bin",
247
- "transformer.h.27.input_layernorm.bias": "pytorch_model-00004-of-00007.bin",
248
- "transformer.h.27.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
249
- "transformer.h.27.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00007.bin",
250
- "transformer.h.27.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00007.bin",
251
- "transformer.h.27.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00007.bin",
252
- "transformer.h.27.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00007.bin",
253
- "transformer.h.27.post_attention_layernorm.bias": "pytorch_model-00004-of-00007.bin",
254
- "transformer.h.27.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
255
- "transformer.h.27.self_attention.dense.bias": "pytorch_model-00004-of-00007.bin",
256
- "transformer.h.27.self_attention.dense.weight": "pytorch_model-00004-of-00007.bin",
257
- "transformer.h.27.self_attention.query_key_value.bias": "pytorch_model-00004-of-00007.bin",
258
- "transformer.h.27.self_attention.query_key_value.weight": "pytorch_model-00004-of-00007.bin",
259
- "transformer.h.28.input_layernorm.bias": "pytorch_model-00004-of-00007.bin",
260
- "transformer.h.28.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
261
- "transformer.h.28.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00007.bin",
262
- "transformer.h.28.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00007.bin",
263
- "transformer.h.28.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00007.bin",
264
- "transformer.h.28.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00007.bin",
265
- "transformer.h.28.post_attention_layernorm.bias": "pytorch_model-00004-of-00007.bin",
266
- "transformer.h.28.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
267
- "transformer.h.28.self_attention.dense.bias": "pytorch_model-00004-of-00007.bin",
268
- "transformer.h.28.self_attention.dense.weight": "pytorch_model-00004-of-00007.bin",
269
- "transformer.h.28.self_attention.query_key_value.bias": "pytorch_model-00004-of-00007.bin",
270
- "transformer.h.28.self_attention.query_key_value.weight": "pytorch_model-00004-of-00007.bin",
271
- "transformer.h.29.input_layernorm.bias": "pytorch_model-00004-of-00007.bin",
272
- "transformer.h.29.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
273
- "transformer.h.29.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00007.bin",
274
- "transformer.h.29.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00007.bin",
275
- "transformer.h.29.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00007.bin",
276
- "transformer.h.29.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00007.bin",
277
- "transformer.h.29.post_attention_layernorm.bias": "pytorch_model-00004-of-00007.bin",
278
- "transformer.h.29.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
279
- "transformer.h.29.self_attention.dense.bias": "pytorch_model-00004-of-00007.bin",
280
- "transformer.h.29.self_attention.dense.weight": "pytorch_model-00004-of-00007.bin",
281
- "transformer.h.29.self_attention.query_key_value.bias": "pytorch_model-00004-of-00007.bin",
282
- "transformer.h.29.self_attention.query_key_value.weight": "pytorch_model-00004-of-00007.bin",
283
- "transformer.h.3.input_layernorm.bias": "pytorch_model-00001-of-00007.bin",
284
- "transformer.h.3.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
285
- "transformer.h.3.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00007.bin",
286
- "transformer.h.3.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00007.bin",
287
- "transformer.h.3.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00007.bin",
288
- "transformer.h.3.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00007.bin",
289
- "transformer.h.3.post_attention_layernorm.bias": "pytorch_model-00001-of-00007.bin",
290
- "transformer.h.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
291
- "transformer.h.3.self_attention.dense.bias": "pytorch_model-00001-of-00007.bin",
292
- "transformer.h.3.self_attention.dense.weight": "pytorch_model-00001-of-00007.bin",
293
- "transformer.h.3.self_attention.query_key_value.bias": "pytorch_model-00001-of-00007.bin",
294
- "transformer.h.3.self_attention.query_key_value.weight": "pytorch_model-00001-of-00007.bin",
295
- "transformer.h.30.input_layernorm.bias": "pytorch_model-00004-of-00007.bin",
296
- "transformer.h.30.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
297
- "transformer.h.30.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00007.bin",
298
- "transformer.h.30.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00007.bin",
299
- "transformer.h.30.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00007.bin",
300
- "transformer.h.30.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00007.bin",
301
- "transformer.h.30.post_attention_layernorm.bias": "pytorch_model-00004-of-00007.bin",
302
- "transformer.h.30.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
303
- "transformer.h.30.self_attention.dense.bias": "pytorch_model-00004-of-00007.bin",
304
- "transformer.h.30.self_attention.dense.weight": "pytorch_model-00004-of-00007.bin",
305
- "transformer.h.30.self_attention.query_key_value.bias": "pytorch_model-00004-of-00007.bin",
306
- "transformer.h.30.self_attention.query_key_value.weight": "pytorch_model-00004-of-00007.bin",
307
- "transformer.h.31.input_layernorm.bias": "pytorch_model-00005-of-00007.bin",
308
- "transformer.h.31.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
309
- "transformer.h.31.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00007.bin",
310
- "transformer.h.31.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00007.bin",
311
- "transformer.h.31.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00007.bin",
312
- "transformer.h.31.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00007.bin",
313
- "transformer.h.31.post_attention_layernorm.bias": "pytorch_model-00005-of-00007.bin",
314
- "transformer.h.31.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
315
- "transformer.h.31.self_attention.dense.bias": "pytorch_model-00005-of-00007.bin",
316
- "transformer.h.31.self_attention.dense.weight": "pytorch_model-00005-of-00007.bin",
317
- "transformer.h.31.self_attention.query_key_value.bias": "pytorch_model-00005-of-00007.bin",
318
- "transformer.h.31.self_attention.query_key_value.weight": "pytorch_model-00005-of-00007.bin",
319
- "transformer.h.32.input_layernorm.bias": "pytorch_model-00005-of-00007.bin",
320
- "transformer.h.32.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
321
- "transformer.h.32.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00007.bin",
322
- "transformer.h.32.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00007.bin",
323
- "transformer.h.32.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00007.bin",
324
- "transformer.h.32.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00007.bin",
325
- "transformer.h.32.post_attention_layernorm.bias": "pytorch_model-00005-of-00007.bin",
326
- "transformer.h.32.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
327
- "transformer.h.32.self_attention.dense.bias": "pytorch_model-00005-of-00007.bin",
328
- "transformer.h.32.self_attention.dense.weight": "pytorch_model-00005-of-00007.bin",
329
- "transformer.h.32.self_attention.query_key_value.bias": "pytorch_model-00005-of-00007.bin",
330
- "transformer.h.32.self_attention.query_key_value.weight": "pytorch_model-00005-of-00007.bin",
331
- "transformer.h.33.input_layernorm.bias": "pytorch_model-00005-of-00007.bin",
332
- "transformer.h.33.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
333
- "transformer.h.33.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00007.bin",
334
- "transformer.h.33.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00007.bin",
335
- "transformer.h.33.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00007.bin",
336
- "transformer.h.33.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00007.bin",
337
- "transformer.h.33.post_attention_layernorm.bias": "pytorch_model-00005-of-00007.bin",
338
- "transformer.h.33.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
339
- "transformer.h.33.self_attention.dense.bias": "pytorch_model-00005-of-00007.bin",
340
- "transformer.h.33.self_attention.dense.weight": "pytorch_model-00005-of-00007.bin",
341
- "transformer.h.33.self_attention.query_key_value.bias": "pytorch_model-00005-of-00007.bin",
342
- "transformer.h.33.self_attention.query_key_value.weight": "pytorch_model-00005-of-00007.bin",
343
- "transformer.h.34.input_layernorm.bias": "pytorch_model-00005-of-00007.bin",
344
- "transformer.h.34.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
345
- "transformer.h.34.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00007.bin",
346
- "transformer.h.34.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00007.bin",
347
- "transformer.h.34.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00007.bin",
348
- "transformer.h.34.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00007.bin",
349
- "transformer.h.34.post_attention_layernorm.bias": "pytorch_model-00005-of-00007.bin",
350
- "transformer.h.34.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
351
- "transformer.h.34.self_attention.dense.bias": "pytorch_model-00005-of-00007.bin",
352
- "transformer.h.34.self_attention.dense.weight": "pytorch_model-00005-of-00007.bin",
353
- "transformer.h.34.self_attention.query_key_value.bias": "pytorch_model-00005-of-00007.bin",
354
- "transformer.h.34.self_attention.query_key_value.weight": "pytorch_model-00005-of-00007.bin",
355
- "transformer.h.35.input_layernorm.bias": "pytorch_model-00005-of-00007.bin",
356
- "transformer.h.35.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
357
- "transformer.h.35.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00007.bin",
358
- "transformer.h.35.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00007.bin",
359
- "transformer.h.35.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00007.bin",
360
- "transformer.h.35.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00007.bin",
361
- "transformer.h.35.post_attention_layernorm.bias": "pytorch_model-00005-of-00007.bin",
362
- "transformer.h.35.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
363
- "transformer.h.35.self_attention.dense.bias": "pytorch_model-00005-of-00007.bin",
364
- "transformer.h.35.self_attention.dense.weight": "pytorch_model-00005-of-00007.bin",
365
- "transformer.h.35.self_attention.query_key_value.bias": "pytorch_model-00005-of-00007.bin",
366
- "transformer.h.35.self_attention.query_key_value.weight": "pytorch_model-00005-of-00007.bin",
367
- "transformer.h.36.input_layernorm.bias": "pytorch_model-00005-of-00007.bin",
368
- "transformer.h.36.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
369
- "transformer.h.36.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00007.bin",
370
- "transformer.h.36.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00007.bin",
371
- "transformer.h.36.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00007.bin",
372
- "transformer.h.36.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00007.bin",
373
- "transformer.h.36.post_attention_layernorm.bias": "pytorch_model-00005-of-00007.bin",
374
- "transformer.h.36.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
375
- "transformer.h.36.self_attention.dense.bias": "pytorch_model-00005-of-00007.bin",
376
- "transformer.h.36.self_attention.dense.weight": "pytorch_model-00005-of-00007.bin",
377
- "transformer.h.36.self_attention.query_key_value.bias": "pytorch_model-00005-of-00007.bin",
378
- "transformer.h.36.self_attention.query_key_value.weight": "pytorch_model-00005-of-00007.bin",
379
- "transformer.h.37.input_layernorm.bias": "pytorch_model-00005-of-00007.bin",
380
- "transformer.h.37.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
381
- "transformer.h.37.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00007.bin",
382
- "transformer.h.37.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00007.bin",
383
- "transformer.h.37.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00007.bin",
384
- "transformer.h.37.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00007.bin",
385
- "transformer.h.37.post_attention_layernorm.bias": "pytorch_model-00005-of-00007.bin",
386
- "transformer.h.37.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
387
- "transformer.h.37.self_attention.dense.bias": "pytorch_model-00005-of-00007.bin",
388
- "transformer.h.37.self_attention.dense.weight": "pytorch_model-00005-of-00007.bin",
389
- "transformer.h.37.self_attention.query_key_value.bias": "pytorch_model-00005-of-00007.bin",
390
- "transformer.h.37.self_attention.query_key_value.weight": "pytorch_model-00005-of-00007.bin",
391
- "transformer.h.38.input_layernorm.bias": "pytorch_model-00005-of-00007.bin",
392
- "transformer.h.38.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
393
- "transformer.h.38.mlp.dense_4h_to_h.bias": "pytorch_model-00006-of-00007.bin",
394
- "transformer.h.38.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00007.bin",
395
- "transformer.h.38.mlp.dense_h_to_4h.bias": "pytorch_model-00006-of-00007.bin",
396
- "transformer.h.38.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00007.bin",
397
- "transformer.h.38.post_attention_layernorm.bias": "pytorch_model-00005-of-00007.bin",
398
- "transformer.h.38.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
399
- "transformer.h.38.self_attention.dense.bias": "pytorch_model-00005-of-00007.bin",
400
- "transformer.h.38.self_attention.dense.weight": "pytorch_model-00005-of-00007.bin",
401
- "transformer.h.38.self_attention.query_key_value.bias": "pytorch_model-00005-of-00007.bin",
402
- "transformer.h.38.self_attention.query_key_value.weight": "pytorch_model-00005-of-00007.bin",
403
- "transformer.h.39.input_layernorm.bias": "pytorch_model-00006-of-00007.bin",
404
- "transformer.h.39.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
405
- "transformer.h.39.mlp.dense_4h_to_h.bias": "pytorch_model-00006-of-00007.bin",
406
- "transformer.h.39.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00007.bin",
407
- "transformer.h.39.mlp.dense_h_to_4h.bias": "pytorch_model-00006-of-00007.bin",
408
- "transformer.h.39.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00007.bin",
409
- "transformer.h.39.post_attention_layernorm.bias": "pytorch_model-00006-of-00007.bin",
410
- "transformer.h.39.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
411
- "transformer.h.39.self_attention.dense.bias": "pytorch_model-00006-of-00007.bin",
412
- "transformer.h.39.self_attention.dense.weight": "pytorch_model-00006-of-00007.bin",
413
- "transformer.h.39.self_attention.query_key_value.bias": "pytorch_model-00006-of-00007.bin",
414
- "transformer.h.39.self_attention.query_key_value.weight": "pytorch_model-00006-of-00007.bin",
415
- "transformer.h.4.input_layernorm.bias": "pytorch_model-00001-of-00007.bin",
416
- "transformer.h.4.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
417
- "transformer.h.4.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00007.bin",
418
- "transformer.h.4.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00007.bin",
419
- "transformer.h.4.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00007.bin",
420
- "transformer.h.4.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00007.bin",
421
- "transformer.h.4.post_attention_layernorm.bias": "pytorch_model-00001-of-00007.bin",
422
- "transformer.h.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
423
- "transformer.h.4.self_attention.dense.bias": "pytorch_model-00001-of-00007.bin",
424
- "transformer.h.4.self_attention.dense.weight": "pytorch_model-00001-of-00007.bin",
425
- "transformer.h.4.self_attention.query_key_value.bias": "pytorch_model-00001-of-00007.bin",
426
- "transformer.h.4.self_attention.query_key_value.weight": "pytorch_model-00001-of-00007.bin",
427
- "transformer.h.40.input_layernorm.bias": "pytorch_model-00006-of-00007.bin",
428
- "transformer.h.40.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
429
- "transformer.h.40.mlp.dense_4h_to_h.bias": "pytorch_model-00006-of-00007.bin",
430
- "transformer.h.40.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00007.bin",
431
- "transformer.h.40.mlp.dense_h_to_4h.bias": "pytorch_model-00006-of-00007.bin",
432
- "transformer.h.40.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00007.bin",
433
- "transformer.h.40.post_attention_layernorm.bias": "pytorch_model-00006-of-00007.bin",
434
- "transformer.h.40.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
435
- "transformer.h.40.self_attention.dense.bias": "pytorch_model-00006-of-00007.bin",
436
- "transformer.h.40.self_attention.dense.weight": "pytorch_model-00006-of-00007.bin",
437
- "transformer.h.40.self_attention.query_key_value.bias": "pytorch_model-00006-of-00007.bin",
438
- "transformer.h.40.self_attention.query_key_value.weight": "pytorch_model-00006-of-00007.bin",
439
- "transformer.h.41.input_layernorm.bias": "pytorch_model-00006-of-00007.bin",
440
- "transformer.h.41.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
441
- "transformer.h.41.mlp.dense_4h_to_h.bias": "pytorch_model-00006-of-00007.bin",
442
- "transformer.h.41.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00007.bin",
443
- "transformer.h.41.mlp.dense_h_to_4h.bias": "pytorch_model-00006-of-00007.bin",
444
- "transformer.h.41.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00007.bin",
445
- "transformer.h.41.post_attention_layernorm.bias": "pytorch_model-00006-of-00007.bin",
446
- "transformer.h.41.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
447
- "transformer.h.41.self_attention.dense.bias": "pytorch_model-00006-of-00007.bin",
448
- "transformer.h.41.self_attention.dense.weight": "pytorch_model-00006-of-00007.bin",
449
- "transformer.h.41.self_attention.query_key_value.bias": "pytorch_model-00006-of-00007.bin",
450
- "transformer.h.41.self_attention.query_key_value.weight": "pytorch_model-00006-of-00007.bin",
451
- "transformer.h.42.input_layernorm.bias": "pytorch_model-00006-of-00007.bin",
452
- "transformer.h.42.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
453
- "transformer.h.42.mlp.dense_4h_to_h.bias": "pytorch_model-00006-of-00007.bin",
454
- "transformer.h.42.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00007.bin",
455
- "transformer.h.42.mlp.dense_h_to_4h.bias": "pytorch_model-00006-of-00007.bin",
456
- "transformer.h.42.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00007.bin",
457
- "transformer.h.42.post_attention_layernorm.bias": "pytorch_model-00006-of-00007.bin",
458
- "transformer.h.42.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
459
- "transformer.h.42.self_attention.dense.bias": "pytorch_model-00006-of-00007.bin",
460
- "transformer.h.42.self_attention.dense.weight": "pytorch_model-00006-of-00007.bin",
461
- "transformer.h.42.self_attention.query_key_value.bias": "pytorch_model-00006-of-00007.bin",
462
- "transformer.h.42.self_attention.query_key_value.weight": "pytorch_model-00006-of-00007.bin",
463
- "transformer.h.43.input_layernorm.bias": "pytorch_model-00006-of-00007.bin",
464
- "transformer.h.43.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
465
- "transformer.h.43.mlp.dense_4h_to_h.bias": "pytorch_model-00006-of-00007.bin",
466
- "transformer.h.43.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00007.bin",
467
- "transformer.h.43.mlp.dense_h_to_4h.bias": "pytorch_model-00006-of-00007.bin",
468
- "transformer.h.43.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00007.bin",
469
- "transformer.h.43.post_attention_layernorm.bias": "pytorch_model-00006-of-00007.bin",
470
- "transformer.h.43.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
471
- "transformer.h.43.self_attention.dense.bias": "pytorch_model-00006-of-00007.bin",
472
- "transformer.h.43.self_attention.dense.weight": "pytorch_model-00006-of-00007.bin",
473
- "transformer.h.43.self_attention.query_key_value.bias": "pytorch_model-00006-of-00007.bin",
474
- "transformer.h.43.self_attention.query_key_value.weight": "pytorch_model-00006-of-00007.bin",
475
- "transformer.h.44.input_layernorm.bias": "pytorch_model-00006-of-00007.bin",
476
- "transformer.h.44.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
477
- "transformer.h.44.mlp.dense_4h_to_h.bias": "pytorch_model-00006-of-00007.bin",
478
- "transformer.h.44.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00007.bin",
479
- "transformer.h.44.mlp.dense_h_to_4h.bias": "pytorch_model-00006-of-00007.bin",
480
- "transformer.h.44.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00007.bin",
481
- "transformer.h.44.post_attention_layernorm.bias": "pytorch_model-00006-of-00007.bin",
482
- "transformer.h.44.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
483
- "transformer.h.44.self_attention.dense.bias": "pytorch_model-00006-of-00007.bin",
484
- "transformer.h.44.self_attention.dense.weight": "pytorch_model-00006-of-00007.bin",
485
- "transformer.h.44.self_attention.query_key_value.bias": "pytorch_model-00006-of-00007.bin",
486
- "transformer.h.44.self_attention.query_key_value.weight": "pytorch_model-00006-of-00007.bin",
487
- "transformer.h.45.input_layernorm.bias": "pytorch_model-00006-of-00007.bin",
488
- "transformer.h.45.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
489
- "transformer.h.45.mlp.dense_4h_to_h.bias": "pytorch_model-00006-of-00007.bin",
490
- "transformer.h.45.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00007.bin",
491
- "transformer.h.45.mlp.dense_h_to_4h.bias": "pytorch_model-00006-of-00007.bin",
492
- "transformer.h.45.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00007.bin",
493
- "transformer.h.45.post_attention_layernorm.bias": "pytorch_model-00006-of-00007.bin",
494
- "transformer.h.45.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
495
- "transformer.h.45.self_attention.dense.bias": "pytorch_model-00006-of-00007.bin",
496
- "transformer.h.45.self_attention.dense.weight": "pytorch_model-00006-of-00007.bin",
497
- "transformer.h.45.self_attention.query_key_value.bias": "pytorch_model-00006-of-00007.bin",
498
- "transformer.h.45.self_attention.query_key_value.weight": "pytorch_model-00006-of-00007.bin",
499
- "transformer.h.46.input_layernorm.bias": "pytorch_model-00006-of-00007.bin",
500
- "transformer.h.46.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
501
- "transformer.h.46.mlp.dense_4h_to_h.bias": "pytorch_model-00007-of-00007.bin",
502
- "transformer.h.46.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00007.bin",
503
- "transformer.h.46.mlp.dense_h_to_4h.bias": "pytorch_model-00007-of-00007.bin",
504
- "transformer.h.46.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00007.bin",
505
- "transformer.h.46.post_attention_layernorm.bias": "pytorch_model-00006-of-00007.bin",
506
- "transformer.h.46.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
507
- "transformer.h.46.self_attention.dense.bias": "pytorch_model-00006-of-00007.bin",
508
- "transformer.h.46.self_attention.dense.weight": "pytorch_model-00006-of-00007.bin",
509
- "transformer.h.46.self_attention.query_key_value.bias": "pytorch_model-00006-of-00007.bin",
510
- "transformer.h.46.self_attention.query_key_value.weight": "pytorch_model-00006-of-00007.bin",
511
- "transformer.h.47.input_layernorm.bias": "pytorch_model-00007-of-00007.bin",
512
- "transformer.h.47.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
513
- "transformer.h.47.mlp.dense_4h_to_h.bias": "pytorch_model-00007-of-00007.bin",
514
- "transformer.h.47.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00007.bin",
515
- "transformer.h.47.mlp.dense_h_to_4h.bias": "pytorch_model-00007-of-00007.bin",
516
- "transformer.h.47.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00007.bin",
517
- "transformer.h.47.post_attention_layernorm.bias": "pytorch_model-00007-of-00007.bin",
518
- "transformer.h.47.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
519
- "transformer.h.47.self_attention.dense.bias": "pytorch_model-00007-of-00007.bin",
520
- "transformer.h.47.self_attention.dense.weight": "pytorch_model-00007-of-00007.bin",
521
- "transformer.h.47.self_attention.query_key_value.bias": "pytorch_model-00007-of-00007.bin",
522
- "transformer.h.47.self_attention.query_key_value.weight": "pytorch_model-00007-of-00007.bin",
523
- "transformer.h.48.input_layernorm.bias": "pytorch_model-00007-of-00007.bin",
524
- "transformer.h.48.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
525
- "transformer.h.48.mlp.dense_4h_to_h.bias": "pytorch_model-00007-of-00007.bin",
526
- "transformer.h.48.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00007.bin",
527
- "transformer.h.48.mlp.dense_h_to_4h.bias": "pytorch_model-00007-of-00007.bin",
528
- "transformer.h.48.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00007.bin",
529
- "transformer.h.48.post_attention_layernorm.bias": "pytorch_model-00007-of-00007.bin",
530
- "transformer.h.48.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
531
- "transformer.h.48.self_attention.dense.bias": "pytorch_model-00007-of-00007.bin",
532
- "transformer.h.48.self_attention.dense.weight": "pytorch_model-00007-of-00007.bin",
533
- "transformer.h.48.self_attention.query_key_value.bias": "pytorch_model-00007-of-00007.bin",
534
- "transformer.h.48.self_attention.query_key_value.weight": "pytorch_model-00007-of-00007.bin",
535
- "transformer.h.49.input_layernorm.bias": "pytorch_model-00007-of-00007.bin",
536
- "transformer.h.49.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
537
- "transformer.h.49.mlp.dense_4h_to_h.bias": "pytorch_model-00007-of-00007.bin",
538
- "transformer.h.49.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00007.bin",
539
- "transformer.h.49.mlp.dense_h_to_4h.bias": "pytorch_model-00007-of-00007.bin",
540
- "transformer.h.49.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00007.bin",
541
- "transformer.h.49.post_attention_layernorm.bias": "pytorch_model-00007-of-00007.bin",
542
- "transformer.h.49.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
543
- "transformer.h.49.self_attention.dense.bias": "pytorch_model-00007-of-00007.bin",
544
- "transformer.h.49.self_attention.dense.weight": "pytorch_model-00007-of-00007.bin",
545
- "transformer.h.49.self_attention.query_key_value.bias": "pytorch_model-00007-of-00007.bin",
546
- "transformer.h.49.self_attention.query_key_value.weight": "pytorch_model-00007-of-00007.bin",
547
- "transformer.h.5.input_layernorm.bias": "pytorch_model-00001-of-00007.bin",
548
- "transformer.h.5.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
549
- "transformer.h.5.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00007.bin",
550
- "transformer.h.5.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00007.bin",
551
- "transformer.h.5.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00007.bin",
552
- "transformer.h.5.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00007.bin",
553
- "transformer.h.5.post_attention_layernorm.bias": "pytorch_model-00001-of-00007.bin",
554
- "transformer.h.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
555
- "transformer.h.5.self_attention.dense.bias": "pytorch_model-00001-of-00007.bin",
556
- "transformer.h.5.self_attention.dense.weight": "pytorch_model-00001-of-00007.bin",
557
- "transformer.h.5.self_attention.query_key_value.bias": "pytorch_model-00001-of-00007.bin",
558
- "transformer.h.5.self_attention.query_key_value.weight": "pytorch_model-00001-of-00007.bin",
559
- "transformer.h.50.input_layernorm.bias": "pytorch_model-00007-of-00007.bin",
560
- "transformer.h.50.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
561
- "transformer.h.50.mlp.dense_4h_to_h.bias": "pytorch_model-00007-of-00007.bin",
562
- "transformer.h.50.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00007.bin",
563
- "transformer.h.50.mlp.dense_h_to_4h.bias": "pytorch_model-00007-of-00007.bin",
564
- "transformer.h.50.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00007.bin",
565
- "transformer.h.50.post_attention_layernorm.bias": "pytorch_model-00007-of-00007.bin",
566
- "transformer.h.50.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
567
- "transformer.h.50.self_attention.dense.bias": "pytorch_model-00007-of-00007.bin",
568
- "transformer.h.50.self_attention.dense.weight": "pytorch_model-00007-of-00007.bin",
569
- "transformer.h.50.self_attention.query_key_value.bias": "pytorch_model-00007-of-00007.bin",
570
- "transformer.h.50.self_attention.query_key_value.weight": "pytorch_model-00007-of-00007.bin",
571
- "transformer.h.51.input_layernorm.bias": "pytorch_model-00007-of-00007.bin",
572
- "transformer.h.51.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
573
- "transformer.h.51.mlp.dense_4h_to_h.bias": "pytorch_model-00007-of-00007.bin",
574
- "transformer.h.51.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00007.bin",
575
- "transformer.h.51.mlp.dense_h_to_4h.bias": "pytorch_model-00007-of-00007.bin",
576
- "transformer.h.51.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00007.bin",
577
- "transformer.h.51.post_attention_layernorm.bias": "pytorch_model-00007-of-00007.bin",
578
- "transformer.h.51.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
579
- "transformer.h.51.self_attention.dense.bias": "pytorch_model-00007-of-00007.bin",
580
- "transformer.h.51.self_attention.dense.weight": "pytorch_model-00007-of-00007.bin",
581
- "transformer.h.51.self_attention.query_key_value.bias": "pytorch_model-00007-of-00007.bin",
582
- "transformer.h.51.self_attention.query_key_value.weight": "pytorch_model-00007-of-00007.bin",
583
- "transformer.h.52.input_layernorm.bias": "pytorch_model-00007-of-00007.bin",
584
- "transformer.h.52.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
585
- "transformer.h.52.mlp.dense_4h_to_h.bias": "pytorch_model-00007-of-00007.bin",
586
- "transformer.h.52.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00007.bin",
587
- "transformer.h.52.mlp.dense_h_to_4h.bias": "pytorch_model-00007-of-00007.bin",
588
- "transformer.h.52.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00007.bin",
589
- "transformer.h.52.post_attention_layernorm.bias": "pytorch_model-00007-of-00007.bin",
590
- "transformer.h.52.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
591
- "transformer.h.52.self_attention.dense.bias": "pytorch_model-00007-of-00007.bin",
592
- "transformer.h.52.self_attention.dense.weight": "pytorch_model-00007-of-00007.bin",
593
- "transformer.h.52.self_attention.query_key_value.bias": "pytorch_model-00007-of-00007.bin",
594
- "transformer.h.52.self_attention.query_key_value.weight": "pytorch_model-00007-of-00007.bin",
595
- "transformer.h.53.input_layernorm.bias": "pytorch_model-00007-of-00007.bin",
596
- "transformer.h.53.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
597
- "transformer.h.53.mlp.dense_4h_to_h.bias": "pytorch_model-00007-of-00007.bin",
598
- "transformer.h.53.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00007.bin",
599
- "transformer.h.53.mlp.dense_h_to_4h.bias": "pytorch_model-00007-of-00007.bin",
600
- "transformer.h.53.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00007.bin",
601
- "transformer.h.53.post_attention_layernorm.bias": "pytorch_model-00007-of-00007.bin",
602
- "transformer.h.53.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
603
- "transformer.h.53.self_attention.dense.bias": "pytorch_model-00007-of-00007.bin",
604
- "transformer.h.53.self_attention.dense.weight": "pytorch_model-00007-of-00007.bin",
605
- "transformer.h.53.self_attention.query_key_value.bias": "pytorch_model-00007-of-00007.bin",
606
- "transformer.h.53.self_attention.query_key_value.weight": "pytorch_model-00007-of-00007.bin",
607
- "transformer.h.6.input_layernorm.bias": "pytorch_model-00001-of-00007.bin",
608
- "transformer.h.6.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
609
- "transformer.h.6.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00007.bin",
610
- "transformer.h.6.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00007.bin",
611
- "transformer.h.6.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00007.bin",
612
- "transformer.h.6.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00007.bin",
613
- "transformer.h.6.post_attention_layernorm.bias": "pytorch_model-00001-of-00007.bin",
614
- "transformer.h.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
615
- "transformer.h.6.self_attention.dense.bias": "pytorch_model-00001-of-00007.bin",
616
- "transformer.h.6.self_attention.dense.weight": "pytorch_model-00001-of-00007.bin",
617
- "transformer.h.6.self_attention.query_key_value.bias": "pytorch_model-00001-of-00007.bin",
618
- "transformer.h.6.self_attention.query_key_value.weight": "pytorch_model-00001-of-00007.bin",
619
- "transformer.h.7.input_layernorm.bias": "pytorch_model-00002-of-00007.bin",
620
- "transformer.h.7.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
621
- "transformer.h.7.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00007.bin",
622
- "transformer.h.7.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00007.bin",
623
- "transformer.h.7.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00007.bin",
624
- "transformer.h.7.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00007.bin",
625
- "transformer.h.7.post_attention_layernorm.bias": "pytorch_model-00002-of-00007.bin",
626
- "transformer.h.7.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
627
- "transformer.h.7.self_attention.dense.bias": "pytorch_model-00002-of-00007.bin",
628
- "transformer.h.7.self_attention.dense.weight": "pytorch_model-00002-of-00007.bin",
629
- "transformer.h.7.self_attention.query_key_value.bias": "pytorch_model-00002-of-00007.bin",
630
- "transformer.h.7.self_attention.query_key_value.weight": "pytorch_model-00002-of-00007.bin",
631
- "transformer.h.8.input_layernorm.bias": "pytorch_model-00002-of-00007.bin",
632
- "transformer.h.8.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
633
- "transformer.h.8.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00007.bin",
634
- "transformer.h.8.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00007.bin",
635
- "transformer.h.8.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00007.bin",
636
- "transformer.h.8.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00007.bin",
637
- "transformer.h.8.post_attention_layernorm.bias": "pytorch_model-00002-of-00007.bin",
638
- "transformer.h.8.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
639
- "transformer.h.8.self_attention.dense.bias": "pytorch_model-00002-of-00007.bin",
640
- "transformer.h.8.self_attention.dense.weight": "pytorch_model-00002-of-00007.bin",
641
- "transformer.h.8.self_attention.query_key_value.bias": "pytorch_model-00002-of-00007.bin",
642
- "transformer.h.8.self_attention.query_key_value.weight": "pytorch_model-00002-of-00007.bin",
643
- "transformer.h.9.input_layernorm.bias": "pytorch_model-00002-of-00007.bin",
644
- "transformer.h.9.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
645
- "transformer.h.9.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00007.bin",
646
- "transformer.h.9.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00007.bin",
647
- "transformer.h.9.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00007.bin",
648
- "transformer.h.9.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00007.bin",
649
- "transformer.h.9.post_attention_layernorm.bias": "pytorch_model-00002-of-00007.bin",
650
- "transformer.h.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
651
- "transformer.h.9.self_attention.dense.bias": "pytorch_model-00002-of-00007.bin",
652
- "transformer.h.9.self_attention.dense.weight": "pytorch_model-00002-of-00007.bin",
653
- "transformer.h.9.self_attention.query_key_value.bias": "pytorch_model-00002-of-00007.bin",
654
- "transformer.h.9.self_attention.query_key_value.weight": "pytorch_model-00002-of-00007.bin",
655
- "transformer.ln_f.bias": "pytorch_model-00007-of-00007.bin",
656
- "transformer.ln_f.weight": "pytorch_model-00007-of-00007.bin",
657
- "transformer.word_embeddings.weight": "pytorch_model-00001-of-00007.bin",
658
- "transformer.word_embeddings_layernorm.bias": "pytorch_model-00001-of-00007.bin",
659
- "transformer.word_embeddings_layernorm.weight": "pytorch_model-00001-of-00007.bin"
660
- }
661
- }