Hugging Face's logo

LazarusNLP
/
bloomz-7b1-mt-fp32

Text Generation
Transformers
JAX
bloom
Eval Results
Inference Endpoints
Model card Files Community
w11wo commited on
Commit
49dedc2
·
1 Parent(s): 42ecfbd

Added Flax Weights

Browse files
Files changed (9) hide show
  1. config.json +1 -1
  2. pytorch_model-00001-of-00006.bin → flax_model-00001-of-00003.msgpack +2 -2
  3. pytorch_model-00002-of-00006.bin → flax_model-00002-of-00003.msgpack +2 -2
  4. pytorch_model-00003-of-00006.bin → flax_model-00003-of-00003.msgpack +2 -2
  5. flax_model.msgpack.index.json +372 -0
  6. pytorch_model-00004-of-00006.bin +0 -3
  7. pytorch_model-00005-of-00006.bin +0 -3
  8. pytorch_model-00006-of-00006.bin +0 -3
  9. pytorch_model.bin.index.json +0 -373
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "bigscience/bloomz-7b1-mt",
3
  "apply_residual_connection_post_layernorm": false,
4
  "architectures": [
5
  "BloomForCausalLM"
 
1
  {
2
+ "_name_or_path": "LazarusNLP/bloomz-7b1-mt-fp32",
3
  "apply_residual_connection_post_layernorm": false,
4
  "architectures": [
5
  "BloomForCausalLM"
pytorch_model-00001-of-00006.bin → flax_model-00001-of-00003.msgpack RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7c96aa3657f67c2e347573529828fefb7e8b92313a891bee0101f672f2c852af
3
- size 4916009496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8157cef7a56eabd7f50f4e5e648a85b5a901a473e26da11d776ff370c59fa67
3
+ size 9950498413
pytorch_model-00002-of-00006.bin → flax_model-00002-of-00003.msgpack RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7585b488323c2e06c3492056f79784f85c51bcb30a8a8e0b71c7162de87e1a51
3
- size 4833140986
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a49a1b5acbbc86a4e7d222083e7d9d5b6483e014f01ac2c07d7588af42a0079
3
+ size 9733396081
pytorch_model-00003-of-00006.bin → flax_model-00003-of-00003.msgpack RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:28c36eabc98212745aa29d6649fea6bf67cb24476cc8813fc5c18c39c6c34fb8
3
- size 4833140986
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9367b1a42b67a854f7f1d3d4342c4f8b9e6a7d74461816a133821d644d458881
3
+ size 8592184075
flax_model.msgpack.index.json ADDED
@@ -0,0 +1,372 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 28276064256
4
+ },
5
+ "weight_map": {
6
+ "transformer/h/0/input_layernorm/bias": "flax_model-00001-of-00003.msgpack",
7
+ "transformer/h/0/input_layernorm/scale": "flax_model-00001-of-00003.msgpack",
8
+ "transformer/h/0/mlp/dense_4h_to_h/bias": "flax_model-00001-of-00003.msgpack",
9
+ "transformer/h/0/mlp/dense_4h_to_h/kernel": "flax_model-00001-of-00003.msgpack",
10
+ "transformer/h/0/mlp/dense_h_to_4h/bias": "flax_model-00001-of-00003.msgpack",
11
+ "transformer/h/0/mlp/dense_h_to_4h/kernel": "flax_model-00001-of-00003.msgpack",
12
+ "transformer/h/0/post_attention_layernorm/bias": "flax_model-00001-of-00003.msgpack",
13
+ "transformer/h/0/post_attention_layernorm/scale": "flax_model-00001-of-00003.msgpack",
14
+ "transformer/h/0/self_attention/dense/bias": "flax_model-00001-of-00003.msgpack",
15
+ "transformer/h/0/self_attention/dense/kernel": "flax_model-00001-of-00003.msgpack",
16
+ "transformer/h/0/self_attention/query_key_value/bias": "flax_model-00001-of-00003.msgpack",
17
+ "transformer/h/0/self_attention/query_key_value/kernel": "flax_model-00001-of-00003.msgpack",
18
+ "transformer/h/1/input_layernorm/bias": "flax_model-00001-of-00003.msgpack",
19
+ "transformer/h/1/input_layernorm/scale": "flax_model-00001-of-00003.msgpack",
20
+ "transformer/h/1/mlp/dense_4h_to_h/bias": "flax_model-00001-of-00003.msgpack",
21
+ "transformer/h/1/mlp/dense_4h_to_h/kernel": "flax_model-00001-of-00003.msgpack",
22
+ "transformer/h/1/mlp/dense_h_to_4h/bias": "flax_model-00001-of-00003.msgpack",
23
+ "transformer/h/1/mlp/dense_h_to_4h/kernel": "flax_model-00001-of-00003.msgpack",
24
+ "transformer/h/1/post_attention_layernorm/bias": "flax_model-00001-of-00003.msgpack",
25
+ "transformer/h/1/post_attention_layernorm/scale": "flax_model-00001-of-00003.msgpack",
26
+ "transformer/h/1/self_attention/dense/bias": "flax_model-00001-of-00003.msgpack",
27
+ "transformer/h/1/self_attention/dense/kernel": "flax_model-00001-of-00003.msgpack",
28
+ "transformer/h/1/self_attention/query_key_value/bias": "flax_model-00001-of-00003.msgpack",
29
+ "transformer/h/1/self_attention/query_key_value/kernel": "flax_model-00001-of-00003.msgpack",
30
+ "transformer/h/10/input_layernorm/bias": "flax_model-00002-of-00003.msgpack",
31
+ "transformer/h/10/input_layernorm/scale": "flax_model-00002-of-00003.msgpack",
32
+ "transformer/h/10/mlp/dense_4h_to_h/bias": "flax_model-00002-of-00003.msgpack",
33
+ "transformer/h/10/mlp/dense_4h_to_h/kernel": "flax_model-00002-of-00003.msgpack",
34
+ "transformer/h/10/mlp/dense_h_to_4h/bias": "flax_model-00002-of-00003.msgpack",
35
+ "transformer/h/10/mlp/dense_h_to_4h/kernel": "flax_model-00002-of-00003.msgpack",
36
+ "transformer/h/10/post_attention_layernorm/bias": "flax_model-00002-of-00003.msgpack",
37
+ "transformer/h/10/post_attention_layernorm/scale": "flax_model-00002-of-00003.msgpack",
38
+ "transformer/h/10/self_attention/dense/bias": "flax_model-00002-of-00003.msgpack",
39
+ "transformer/h/10/self_attention/dense/kernel": "flax_model-00002-of-00003.msgpack",
40
+ "transformer/h/10/self_attention/query_key_value/bias": "flax_model-00002-of-00003.msgpack",
41
+ "transformer/h/10/self_attention/query_key_value/kernel": "flax_model-00002-of-00003.msgpack",
42
+ "transformer/h/11/input_layernorm/bias": "flax_model-00002-of-00003.msgpack",
43
+ "transformer/h/11/input_layernorm/scale": "flax_model-00002-of-00003.msgpack",
44
+ "transformer/h/11/mlp/dense_4h_to_h/bias": "flax_model-00002-of-00003.msgpack",
45
+ "transformer/h/11/mlp/dense_4h_to_h/kernel": "flax_model-00002-of-00003.msgpack",
46
+ "transformer/h/11/mlp/dense_h_to_4h/bias": "flax_model-00002-of-00003.msgpack",
47
+ "transformer/h/11/mlp/dense_h_to_4h/kernel": "flax_model-00002-of-00003.msgpack",
48
+ "transformer/h/11/post_attention_layernorm/bias": "flax_model-00002-of-00003.msgpack",
49
+ "transformer/h/11/post_attention_layernorm/scale": "flax_model-00002-of-00003.msgpack",
50
+ "transformer/h/11/self_attention/dense/bias": "flax_model-00002-of-00003.msgpack",
51
+ "transformer/h/11/self_attention/dense/kernel": "flax_model-00002-of-00003.msgpack",
52
+ "transformer/h/11/self_attention/query_key_value/bias": "flax_model-00002-of-00003.msgpack",
53
+ "transformer/h/11/self_attention/query_key_value/kernel": "flax_model-00002-of-00003.msgpack",
54
+ "transformer/h/12/input_layernorm/bias": "flax_model-00002-of-00003.msgpack",
55
+ "transformer/h/12/input_layernorm/scale": "flax_model-00002-of-00003.msgpack",
56
+ "transformer/h/12/mlp/dense_4h_to_h/bias": "flax_model-00002-of-00003.msgpack",
57
+ "transformer/h/12/mlp/dense_4h_to_h/kernel": "flax_model-00002-of-00003.msgpack",
58
+ "transformer/h/12/mlp/dense_h_to_4h/bias": "flax_model-00002-of-00003.msgpack",
59
+ "transformer/h/12/mlp/dense_h_to_4h/kernel": "flax_model-00002-of-00003.msgpack",
60
+ "transformer/h/12/post_attention_layernorm/bias": "flax_model-00002-of-00003.msgpack",
61
+ "transformer/h/12/post_attention_layernorm/scale": "flax_model-00002-of-00003.msgpack",
62
+ "transformer/h/12/self_attention/dense/bias": "flax_model-00002-of-00003.msgpack",
63
+ "transformer/h/12/self_attention/dense/kernel": "flax_model-00002-of-00003.msgpack",
64
+ "transformer/h/12/self_attention/query_key_value/bias": "flax_model-00002-of-00003.msgpack",
65
+ "transformer/h/12/self_attention/query_key_value/kernel": "flax_model-00002-of-00003.msgpack",
66
+ "transformer/h/13/input_layernorm/bias": "flax_model-00002-of-00003.msgpack",
67
+ "transformer/h/13/input_layernorm/scale": "flax_model-00002-of-00003.msgpack",
68
+ "transformer/h/13/mlp/dense_4h_to_h/bias": "flax_model-00002-of-00003.msgpack",
69
+ "transformer/h/13/mlp/dense_4h_to_h/kernel": "flax_model-00002-of-00003.msgpack",
70
+ "transformer/h/13/mlp/dense_h_to_4h/bias": "flax_model-00002-of-00003.msgpack",
71
+ "transformer/h/13/mlp/dense_h_to_4h/kernel": "flax_model-00002-of-00003.msgpack",
72
+ "transformer/h/13/post_attention_layernorm/bias": "flax_model-00002-of-00003.msgpack",
73
+ "transformer/h/13/post_attention_layernorm/scale": "flax_model-00002-of-00003.msgpack",
74
+ "transformer/h/13/self_attention/dense/bias": "flax_model-00002-of-00003.msgpack",
75
+ "transformer/h/13/self_attention/dense/kernel": "flax_model-00002-of-00003.msgpack",
76
+ "transformer/h/13/self_attention/query_key_value/bias": "flax_model-00002-of-00003.msgpack",
77
+ "transformer/h/13/self_attention/query_key_value/kernel": "flax_model-00002-of-00003.msgpack",
78
+ "transformer/h/14/input_layernorm/bias": "flax_model-00002-of-00003.msgpack",
79
+ "transformer/h/14/input_layernorm/scale": "flax_model-00002-of-00003.msgpack",
80
+ "transformer/h/14/mlp/dense_4h_to_h/bias": "flax_model-00002-of-00003.msgpack",
81
+ "transformer/h/14/mlp/dense_4h_to_h/kernel": "flax_model-00002-of-00003.msgpack",
82
+ "transformer/h/14/mlp/dense_h_to_4h/bias": "flax_model-00002-of-00003.msgpack",
83
+ "transformer/h/14/mlp/dense_h_to_4h/kernel": "flax_model-00002-of-00003.msgpack",
84
+ "transformer/h/14/post_attention_layernorm/bias": "flax_model-00002-of-00003.msgpack",
85
+ "transformer/h/14/post_attention_layernorm/scale": "flax_model-00002-of-00003.msgpack",
86
+ "transformer/h/14/self_attention/dense/bias": "flax_model-00002-of-00003.msgpack",
87
+ "transformer/h/14/self_attention/dense/kernel": "flax_model-00002-of-00003.msgpack",
88
+ "transformer/h/14/self_attention/query_key_value/bias": "flax_model-00002-of-00003.msgpack",
89
+ "transformer/h/14/self_attention/query_key_value/kernel": "flax_model-00002-of-00003.msgpack",
90
+ "transformer/h/15/input_layernorm/bias": "flax_model-00002-of-00003.msgpack",
91
+ "transformer/h/15/input_layernorm/scale": "flax_model-00002-of-00003.msgpack",
92
+ "transformer/h/15/mlp/dense_4h_to_h/bias": "flax_model-00002-of-00003.msgpack",
93
+ "transformer/h/15/mlp/dense_4h_to_h/kernel": "flax_model-00002-of-00003.msgpack",
94
+ "transformer/h/15/mlp/dense_h_to_4h/bias": "flax_model-00002-of-00003.msgpack",
95
+ "transformer/h/15/mlp/dense_h_to_4h/kernel": "flax_model-00002-of-00003.msgpack",
96
+ "transformer/h/15/post_attention_layernorm/bias": "flax_model-00002-of-00003.msgpack",
97
+ "transformer/h/15/post_attention_layernorm/scale": "flax_model-00002-of-00003.msgpack",
98
+ "transformer/h/15/self_attention/dense/bias": "flax_model-00002-of-00003.msgpack",
99
+ "transformer/h/15/self_attention/dense/kernel": "flax_model-00002-of-00003.msgpack",
100
+ "transformer/h/15/self_attention/query_key_value/bias": "flax_model-00002-of-00003.msgpack",
101
+ "transformer/h/15/self_attention/query_key_value/kernel": "flax_model-00002-of-00003.msgpack",
102
+ "transformer/h/16/input_layernorm/bias": "flax_model-00002-of-00003.msgpack",
103
+ "transformer/h/16/input_layernorm/scale": "flax_model-00002-of-00003.msgpack",
104
+ "transformer/h/16/mlp/dense_4h_to_h/bias": "flax_model-00002-of-00003.msgpack",
105
+ "transformer/h/16/mlp/dense_4h_to_h/kernel": "flax_model-00002-of-00003.msgpack",
106
+ "transformer/h/16/mlp/dense_h_to_4h/bias": "flax_model-00002-of-00003.msgpack",
107
+ "transformer/h/16/mlp/dense_h_to_4h/kernel": "flax_model-00002-of-00003.msgpack",
108
+ "transformer/h/16/post_attention_layernorm/bias": "flax_model-00002-of-00003.msgpack",
109
+ "transformer/h/16/post_attention_layernorm/scale": "flax_model-00002-of-00003.msgpack",
110
+ "transformer/h/16/self_attention/dense/bias": "flax_model-00002-of-00003.msgpack",
111
+ "transformer/h/16/self_attention/dense/kernel": "flax_model-00002-of-00003.msgpack",
112
+ "transformer/h/16/self_attention/query_key_value/bias": "flax_model-00002-of-00003.msgpack",
113
+ "transformer/h/16/self_attention/query_key_value/kernel": "flax_model-00002-of-00003.msgpack",
114
+ "transformer/h/17/input_layernorm/bias": "flax_model-00002-of-00003.msgpack",
115
+ "transformer/h/17/input_layernorm/scale": "flax_model-00002-of-00003.msgpack",
116
+ "transformer/h/17/mlp/dense_4h_to_h/bias": "flax_model-00002-of-00003.msgpack",
117
+ "transformer/h/17/mlp/dense_4h_to_h/kernel": "flax_model-00002-of-00003.msgpack",
118
+ "transformer/h/17/mlp/dense_h_to_4h/bias": "flax_model-00002-of-00003.msgpack",
119
+ "transformer/h/17/mlp/dense_h_to_4h/kernel": "flax_model-00002-of-00003.msgpack",
120
+ "transformer/h/17/post_attention_layernorm/bias": "flax_model-00002-of-00003.msgpack",
121
+ "transformer/h/17/post_attention_layernorm/scale": "flax_model-00002-of-00003.msgpack",
122
+ "transformer/h/17/self_attention/dense/bias": "flax_model-00002-of-00003.msgpack",
123
+ "transformer/h/17/self_attention/dense/kernel": "flax_model-00002-of-00003.msgpack",
124
+ "transformer/h/17/self_attention/query_key_value/bias": "flax_model-00002-of-00003.msgpack",
125
+ "transformer/h/17/self_attention/query_key_value/kernel": "flax_model-00002-of-00003.msgpack",
126
+ "transformer/h/18/input_layernorm/bias": "flax_model-00002-of-00003.msgpack",
127
+ "transformer/h/18/input_layernorm/scale": "flax_model-00002-of-00003.msgpack",
128
+ "transformer/h/18/mlp/dense_4h_to_h/bias": "flax_model-00002-of-00003.msgpack",
129
+ "transformer/h/18/mlp/dense_4h_to_h/kernel": "flax_model-00002-of-00003.msgpack",
130
+ "transformer/h/18/mlp/dense_h_to_4h/bias": "flax_model-00002-of-00003.msgpack",
131
+ "transformer/h/18/mlp/dense_h_to_4h/kernel": "flax_model-00002-of-00003.msgpack",
132
+ "transformer/h/18/post_attention_layernorm/bias": "flax_model-00002-of-00003.msgpack",
133
+ "transformer/h/18/post_attention_layernorm/scale": "flax_model-00002-of-00003.msgpack",
134
+ "transformer/h/18/self_attention/dense/bias": "flax_model-00002-of-00003.msgpack",
135
+ "transformer/h/18/self_attention/dense/kernel": "flax_model-00002-of-00003.msgpack",
136
+ "transformer/h/18/self_attention/query_key_value/bias": "flax_model-00002-of-00003.msgpack",
137
+ "transformer/h/18/self_attention/query_key_value/kernel": "flax_model-00002-of-00003.msgpack",
138
+ "transformer/h/19/input_layernorm/bias": "flax_model-00002-of-00003.msgpack",
139
+ "transformer/h/19/input_layernorm/scale": "flax_model-00002-of-00003.msgpack",
140
+ "transformer/h/19/mlp/dense_4h_to_h/bias": "flax_model-00003-of-00003.msgpack",
141
+ "transformer/h/19/mlp/dense_4h_to_h/kernel": "flax_model-00003-of-00003.msgpack",
142
+ "transformer/h/19/mlp/dense_h_to_4h/bias": "flax_model-00003-of-00003.msgpack",
143
+ "transformer/h/19/mlp/dense_h_to_4h/kernel": "flax_model-00003-of-00003.msgpack",
144
+ "transformer/h/19/post_attention_layernorm/bias": "flax_model-00002-of-00003.msgpack",
145
+ "transformer/h/19/post_attention_layernorm/scale": "flax_model-00002-of-00003.msgpack",
146
+ "transformer/h/19/self_attention/dense/bias": "flax_model-00002-of-00003.msgpack",
147
+ "transformer/h/19/self_attention/dense/kernel": "flax_model-00002-of-00003.msgpack",
148
+ "transformer/h/19/self_attention/query_key_value/bias": "flax_model-00002-of-00003.msgpack",
149
+ "transformer/h/19/self_attention/query_key_value/kernel": "flax_model-00002-of-00003.msgpack",
150
+ "transformer/h/2/input_layernorm/bias": "flax_model-00001-of-00003.msgpack",
151
+ "transformer/h/2/input_layernorm/scale": "flax_model-00001-of-00003.msgpack",
152
+ "transformer/h/2/mlp/dense_4h_to_h/bias": "flax_model-00001-of-00003.msgpack",
153
+ "transformer/h/2/mlp/dense_4h_to_h/kernel": "flax_model-00001-of-00003.msgpack",
154
+ "transformer/h/2/mlp/dense_h_to_4h/bias": "flax_model-00001-of-00003.msgpack",
155
+ "transformer/h/2/mlp/dense_h_to_4h/kernel": "flax_model-00001-of-00003.msgpack",
156
+ "transformer/h/2/post_attention_layernorm/bias": "flax_model-00001-of-00003.msgpack",
157
+ "transformer/h/2/post_attention_layernorm/scale": "flax_model-00001-of-00003.msgpack",
158
+ "transformer/h/2/self_attention/dense/bias": "flax_model-00001-of-00003.msgpack",
159
+ "transformer/h/2/self_attention/dense/kernel": "flax_model-00001-of-00003.msgpack",
160
+ "transformer/h/2/self_attention/query_key_value/bias": "flax_model-00001-of-00003.msgpack",
161
+ "transformer/h/2/self_attention/query_key_value/kernel": "flax_model-00001-of-00003.msgpack",
162
+ "transformer/h/20/input_layernorm/bias": "flax_model-00003-of-00003.msgpack",
163
+ "transformer/h/20/input_layernorm/scale": "flax_model-00003-of-00003.msgpack",
164
+ "transformer/h/20/mlp/dense_4h_to_h/bias": "flax_model-00003-of-00003.msgpack",
165
+ "transformer/h/20/mlp/dense_4h_to_h/kernel": "flax_model-00003-of-00003.msgpack",
166
+ "transformer/h/20/mlp/dense_h_to_4h/bias": "flax_model-00003-of-00003.msgpack",
167
+ "transformer/h/20/mlp/dense_h_to_4h/kernel": "flax_model-00003-of-00003.msgpack",
168
+ "transformer/h/20/post_attention_layernorm/bias": "flax_model-00003-of-00003.msgpack",
169
+ "transformer/h/20/post_attention_layernorm/scale": "flax_model-00003-of-00003.msgpack",
170
+ "transformer/h/20/self_attention/dense/bias": "flax_model-00003-of-00003.msgpack",
171
+ "transformer/h/20/self_attention/dense/kernel": "flax_model-00003-of-00003.msgpack",
172
+ "transformer/h/20/self_attention/query_key_value/bias": "flax_model-00003-of-00003.msgpack",
173
+ "transformer/h/20/self_attention/query_key_value/kernel": "flax_model-00003-of-00003.msgpack",
174
+ "transformer/h/21/input_layernorm/bias": "flax_model-00003-of-00003.msgpack",
175
+ "transformer/h/21/input_layernorm/scale": "flax_model-00003-of-00003.msgpack",
176
+ "transformer/h/21/mlp/dense_4h_to_h/bias": "flax_model-00003-of-00003.msgpack",
177
+ "transformer/h/21/mlp/dense_4h_to_h/kernel": "flax_model-00003-of-00003.msgpack",
178
+ "transformer/h/21/mlp/dense_h_to_4h/bias": "flax_model-00003-of-00003.msgpack",
179
+ "transformer/h/21/mlp/dense_h_to_4h/kernel": "flax_model-00003-of-00003.msgpack",
180
+ "transformer/h/21/post_attention_layernorm/bias": "flax_model-00003-of-00003.msgpack",
181
+ "transformer/h/21/post_attention_layernorm/scale": "flax_model-00003-of-00003.msgpack",
182
+ "transformer/h/21/self_attention/dense/bias": "flax_model-00003-of-00003.msgpack",
183
+ "transformer/h/21/self_attention/dense/kernel": "flax_model-00003-of-00003.msgpack",
184
+ "transformer/h/21/self_attention/query_key_value/bias": "flax_model-00003-of-00003.msgpack",
185
+ "transformer/h/21/self_attention/query_key_value/kernel": "flax_model-00003-of-00003.msgpack",
186
+ "transformer/h/22/input_layernorm/bias": "flax_model-00003-of-00003.msgpack",
187
+ "transformer/h/22/input_layernorm/scale": "flax_model-00003-of-00003.msgpack",
188
+ "transformer/h/22/mlp/dense_4h_to_h/bias": "flax_model-00003-of-00003.msgpack",
189
+ "transformer/h/22/mlp/dense_4h_to_h/kernel": "flax_model-00003-of-00003.msgpack",
190
+ "transformer/h/22/mlp/dense_h_to_4h/bias": "flax_model-00003-of-00003.msgpack",
191
+ "transformer/h/22/mlp/dense_h_to_4h/kernel": "flax_model-00003-of-00003.msgpack",
192
+ "transformer/h/22/post_attention_layernorm/bias": "flax_model-00003-of-00003.msgpack",
193
+ "transformer/h/22/post_attention_layernorm/scale": "flax_model-00003-of-00003.msgpack",
194
+ "transformer/h/22/self_attention/dense/bias": "flax_model-00003-of-00003.msgpack",
195
+ "transformer/h/22/self_attention/dense/kernel": "flax_model-00003-of-00003.msgpack",
196
+ "transformer/h/22/self_attention/query_key_value/bias": "flax_model-00003-of-00003.msgpack",
197
+ "transformer/h/22/self_attention/query_key_value/kernel": "flax_model-00003-of-00003.msgpack",
198
+ "transformer/h/23/input_layernorm/bias": "flax_model-00003-of-00003.msgpack",
199
+ "transformer/h/23/input_layernorm/scale": "flax_model-00003-of-00003.msgpack",
200
+ "transformer/h/23/mlp/dense_4h_to_h/bias": "flax_model-00003-of-00003.msgpack",
201
+ "transformer/h/23/mlp/dense_4h_to_h/kernel": "flax_model-00003-of-00003.msgpack",
202
+ "transformer/h/23/mlp/dense_h_to_4h/bias": "flax_model-00003-of-00003.msgpack",
203
+ "transformer/h/23/mlp/dense_h_to_4h/kernel": "flax_model-00003-of-00003.msgpack",
204
+ "transformer/h/23/post_attention_layernorm/bias": "flax_model-00003-of-00003.msgpack",
205
+ "transformer/h/23/post_attention_layernorm/scale": "flax_model-00003-of-00003.msgpack",
206
+ "transformer/h/23/self_attention/dense/bias": "flax_model-00003-of-00003.msgpack",
207
+ "transformer/h/23/self_attention/dense/kernel": "flax_model-00003-of-00003.msgpack",
208
+ "transformer/h/23/self_attention/query_key_value/bias": "flax_model-00003-of-00003.msgpack",
209
+ "transformer/h/23/self_attention/query_key_value/kernel": "flax_model-00003-of-00003.msgpack",
210
+ "transformer/h/24/input_layernorm/bias": "flax_model-00003-of-00003.msgpack",
211
+ "transformer/h/24/input_layernorm/scale": "flax_model-00003-of-00003.msgpack",
212
+ "transformer/h/24/mlp/dense_4h_to_h/bias": "flax_model-00003-of-00003.msgpack",
213
+ "transformer/h/24/mlp/dense_4h_to_h/kernel": "flax_model-00003-of-00003.msgpack",
214
+ "transformer/h/24/mlp/dense_h_to_4h/bias": "flax_model-00003-of-00003.msgpack",
215
+ "transformer/h/24/mlp/dense_h_to_4h/kernel": "flax_model-00003-of-00003.msgpack",
216
+ "transformer/h/24/post_attention_layernorm/bias": "flax_model-00003-of-00003.msgpack",
217
+ "transformer/h/24/post_attention_layernorm/scale": "flax_model-00003-of-00003.msgpack",
218
+ "transformer/h/24/self_attention/dense/bias": "flax_model-00003-of-00003.msgpack",
219
+ "transformer/h/24/self_attention/dense/kernel": "flax_model-00003-of-00003.msgpack",
220
+ "transformer/h/24/self_attention/query_key_value/bias": "flax_model-00003-of-00003.msgpack",
221
+ "transformer/h/24/self_attention/query_key_value/kernel": "flax_model-00003-of-00003.msgpack",
222
+ "transformer/h/25/input_layernorm/bias": "flax_model-00003-of-00003.msgpack",
223
+ "transformer/h/25/input_layernorm/scale": "flax_model-00003-of-00003.msgpack",
224
+ "transformer/h/25/mlp/dense_4h_to_h/bias": "flax_model-00003-of-00003.msgpack",
225
+ "transformer/h/25/mlp/dense_4h_to_h/kernel": "flax_model-00003-of-00003.msgpack",
226
+ "transformer/h/25/mlp/dense_h_to_4h/bias": "flax_model-00003-of-00003.msgpack",
227
+ "transformer/h/25/mlp/dense_h_to_4h/kernel": "flax_model-00003-of-00003.msgpack",
228
+ "transformer/h/25/post_attention_layernorm/bias": "flax_model-00003-of-00003.msgpack",
229
+ "transformer/h/25/post_attention_layernorm/scale": "flax_model-00003-of-00003.msgpack",
230
+ "transformer/h/25/self_attention/dense/bias": "flax_model-00003-of-00003.msgpack",
231
+ "transformer/h/25/self_attention/dense/kernel": "flax_model-00003-of-00003.msgpack",
232
+ "transformer/h/25/self_attention/query_key_value/bias": "flax_model-00003-of-00003.msgpack",
233
+ "transformer/h/25/self_attention/query_key_value/kernel": "flax_model-00003-of-00003.msgpack",
234
+ "transformer/h/26/input_layernorm/bias": "flax_model-00003-of-00003.msgpack",
235
+ "transformer/h/26/input_layernorm/scale": "flax_model-00003-of-00003.msgpack",
236
+ "transformer/h/26/mlp/dense_4h_to_h/bias": "flax_model-00003-of-00003.msgpack",
237
+ "transformer/h/26/mlp/dense_4h_to_h/kernel": "flax_model-00003-of-00003.msgpack",
238
+ "transformer/h/26/mlp/dense_h_to_4h/bias": "flax_model-00003-of-00003.msgpack",
239
+ "transformer/h/26/mlp/dense_h_to_4h/kernel": "flax_model-00003-of-00003.msgpack",
240
+ "transformer/h/26/post_attention_layernorm/bias": "flax_model-00003-of-00003.msgpack",
241
+ "transformer/h/26/post_attention_layernorm/scale": "flax_model-00003-of-00003.msgpack",
242
+ "transformer/h/26/self_attention/dense/bias": "flax_model-00003-of-00003.msgpack",
243
+ "transformer/h/26/self_attention/dense/kernel": "flax_model-00003-of-00003.msgpack",
244
+ "transformer/h/26/self_attention/query_key_value/bias": "flax_model-00003-of-00003.msgpack",
245
+ "transformer/h/26/self_attention/query_key_value/kernel": "flax_model-00003-of-00003.msgpack",
246
+ "transformer/h/27/input_layernorm/bias": "flax_model-00003-of-00003.msgpack",
247
+ "transformer/h/27/input_layernorm/scale": "flax_model-00003-of-00003.msgpack",
248
+ "transformer/h/27/mlp/dense_4h_to_h/bias": "flax_model-00003-of-00003.msgpack",
249
+ "transformer/h/27/mlp/dense_4h_to_h/kernel": "flax_model-00003-of-00003.msgpack",
250
+ "transformer/h/27/mlp/dense_h_to_4h/bias": "flax_model-00003-of-00003.msgpack",
251
+ "transformer/h/27/mlp/dense_h_to_4h/kernel": "flax_model-00003-of-00003.msgpack",
252
+ "transformer/h/27/post_attention_layernorm/bias": "flax_model-00003-of-00003.msgpack",
253
+ "transformer/h/27/post_attention_layernorm/scale": "flax_model-00003-of-00003.msgpack",
254
+ "transformer/h/27/self_attention/dense/bias": "flax_model-00003-of-00003.msgpack",
255
+ "transformer/h/27/self_attention/dense/kernel": "flax_model-00003-of-00003.msgpack",
256
+ "transformer/h/27/self_attention/query_key_value/bias": "flax_model-00003-of-00003.msgpack",
257
+ "transformer/h/27/self_attention/query_key_value/kernel": "flax_model-00003-of-00003.msgpack",
258
+ "transformer/h/28/input_layernorm/bias": "flax_model-00003-of-00003.msgpack",
259
+ "transformer/h/28/input_layernorm/scale": "flax_model-00003-of-00003.msgpack",
260
+ "transformer/h/28/mlp/dense_4h_to_h/bias": "flax_model-00003-of-00003.msgpack",
261
+ "transformer/h/28/mlp/dense_4h_to_h/kernel": "flax_model-00003-of-00003.msgpack",
262
+ "transformer/h/28/mlp/dense_h_to_4h/bias": "flax_model-00003-of-00003.msgpack",
263
+ "transformer/h/28/mlp/dense_h_to_4h/kernel": "flax_model-00003-of-00003.msgpack",
264
+ "transformer/h/28/post_attention_layernorm/bias": "flax_model-00003-of-00003.msgpack",
265
+ "transformer/h/28/post_attention_layernorm/scale": "flax_model-00003-of-00003.msgpack",
266
+ "transformer/h/28/self_attention/dense/bias": "flax_model-00003-of-00003.msgpack",
267
+ "transformer/h/28/self_attention/dense/kernel": "flax_model-00003-of-00003.msgpack",
268
+ "transformer/h/28/self_attention/query_key_value/bias": "flax_model-00003-of-00003.msgpack",
269
+ "transformer/h/28/self_attention/query_key_value/kernel": "flax_model-00003-of-00003.msgpack",
270
+ "transformer/h/29/input_layernorm/bias": "flax_model-00003-of-00003.msgpack",
271
+ "transformer/h/29/input_layernorm/scale": "flax_model-00003-of-00003.msgpack",
272
+ "transformer/h/29/mlp/dense_4h_to_h/bias": "flax_model-00003-of-00003.msgpack",
273
+ "transformer/h/29/mlp/dense_4h_to_h/kernel": "flax_model-00003-of-00003.msgpack",
274
+ "transformer/h/29/mlp/dense_h_to_4h/bias": "flax_model-00003-of-00003.msgpack",
275
+ "transformer/h/29/mlp/dense_h_to_4h/kernel": "flax_model-00003-of-00003.msgpack",
276
+ "transformer/h/29/post_attention_layernorm/bias": "flax_model-00003-of-00003.msgpack",
277
+ "transformer/h/29/post_attention_layernorm/scale": "flax_model-00003-of-00003.msgpack",
278
+ "transformer/h/29/self_attention/dense/bias": "flax_model-00003-of-00003.msgpack",
279
+ "transformer/h/29/self_attention/dense/kernel": "flax_model-00003-of-00003.msgpack",
280
+ "transformer/h/29/self_attention/query_key_value/bias": "flax_model-00003-of-00003.msgpack",
281
+ "transformer/h/29/self_attention/query_key_value/kernel": "flax_model-00003-of-00003.msgpack",
282
+ "transformer/h/3/input_layernorm/bias": "flax_model-00001-of-00003.msgpack",
283
+ "transformer/h/3/input_layernorm/scale": "flax_model-00001-of-00003.msgpack",
284
+ "transformer/h/3/mlp/dense_4h_to_h/bias": "flax_model-00001-of-00003.msgpack",
285
+ "transformer/h/3/mlp/dense_4h_to_h/kernel": "flax_model-00001-of-00003.msgpack",
286
+ "transformer/h/3/mlp/dense_h_to_4h/bias": "flax_model-00001-of-00003.msgpack",
287
+ "transformer/h/3/mlp/dense_h_to_4h/kernel": "flax_model-00001-of-00003.msgpack",
288
+ "transformer/h/3/post_attention_layernorm/bias": "flax_model-00001-of-00003.msgpack",
289
+ "transformer/h/3/post_attention_layernorm/scale": "flax_model-00001-of-00003.msgpack",
290
+ "transformer/h/3/self_attention/dense/bias": "flax_model-00001-of-00003.msgpack",
291
+ "transformer/h/3/self_attention/dense/kernel": "flax_model-00001-of-00003.msgpack",
292
+ "transformer/h/3/self_attention/query_key_value/bias": "flax_model-00001-of-00003.msgpack",
293
+ "transformer/h/3/self_attention/query_key_value/kernel": "flax_model-00001-of-00003.msgpack",
294
+ "transformer/h/4/input_layernorm/bias": "flax_model-00001-of-00003.msgpack",
295
+ "transformer/h/4/input_layernorm/scale": "flax_model-00001-of-00003.msgpack",
296
+ "transformer/h/4/mlp/dense_4h_to_h/bias": "flax_model-00001-of-00003.msgpack",
297
+ "transformer/h/4/mlp/dense_4h_to_h/kernel": "flax_model-00001-of-00003.msgpack",
298
+ "transformer/h/4/mlp/dense_h_to_4h/bias": "flax_model-00001-of-00003.msgpack",
299
+ "transformer/h/4/mlp/dense_h_to_4h/kernel": "flax_model-00001-of-00003.msgpack",
300
+ "transformer/h/4/post_attention_layernorm/bias": "flax_model-00001-of-00003.msgpack",
301
+ "transformer/h/4/post_attention_layernorm/scale": "flax_model-00001-of-00003.msgpack",
302
+ "transformer/h/4/self_attention/dense/bias": "flax_model-00001-of-00003.msgpack",
303
+ "transformer/h/4/self_attention/dense/kernel": "flax_model-00001-of-00003.msgpack",
304
+ "transformer/h/4/self_attention/query_key_value/bias": "flax_model-00001-of-00003.msgpack",
305
+ "transformer/h/4/self_attention/query_key_value/kernel": "flax_model-00001-of-00003.msgpack",
306
+ "transformer/h/5/input_layernorm/bias": "flax_model-00001-of-00003.msgpack",
307
+ "transformer/h/5/input_layernorm/scale": "flax_model-00001-of-00003.msgpack",
308
+ "transformer/h/5/mlp/dense_4h_to_h/bias": "flax_model-00001-of-00003.msgpack",
309
+ "transformer/h/5/mlp/dense_4h_to_h/kernel": "flax_model-00001-of-00003.msgpack",
310
+ "transformer/h/5/mlp/dense_h_to_4h/bias": "flax_model-00001-of-00003.msgpack",
311
+ "transformer/h/5/mlp/dense_h_to_4h/kernel": "flax_model-00001-of-00003.msgpack",
312
+ "transformer/h/5/post_attention_layernorm/bias": "flax_model-00001-of-00003.msgpack",
313
+ "transformer/h/5/post_attention_layernorm/scale": "flax_model-00001-of-00003.msgpack",
314
+ "transformer/h/5/self_attention/dense/bias": "flax_model-00001-of-00003.msgpack",
315
+ "transformer/h/5/self_attention/dense/kernel": "flax_model-00001-of-00003.msgpack",
316
+ "transformer/h/5/self_attention/query_key_value/bias": "flax_model-00001-of-00003.msgpack",
317
+ "transformer/h/5/self_attention/query_key_value/kernel": "flax_model-00001-of-00003.msgpack",
318
+ "transformer/h/6/input_layernorm/bias": "flax_model-00001-of-00003.msgpack",
319
+ "transformer/h/6/input_layernorm/scale": "flax_model-00001-of-00003.msgpack",
320
+ "transformer/h/6/mlp/dense_4h_to_h/bias": "flax_model-00001-of-00003.msgpack",
321
+ "transformer/h/6/mlp/dense_4h_to_h/kernel": "flax_model-00001-of-00003.msgpack",
322
+ "transformer/h/6/mlp/dense_h_to_4h/bias": "flax_model-00001-of-00003.msgpack",
323
+ "transformer/h/6/mlp/dense_h_to_4h/kernel": "flax_model-00001-of-00003.msgpack",
324
+ "transformer/h/6/post_attention_layernorm/bias": "flax_model-00001-of-00003.msgpack",
325
+ "transformer/h/6/post_attention_layernorm/scale": "flax_model-00001-of-00003.msgpack",
326
+ "transformer/h/6/self_attention/dense/bias": "flax_model-00001-of-00003.msgpack",
327
+ "transformer/h/6/self_attention/dense/kernel": "flax_model-00001-of-00003.msgpack",
328
+ "transformer/h/6/self_attention/query_key_value/bias": "flax_model-00001-of-00003.msgpack",
329
+ "transformer/h/6/self_attention/query_key_value/kernel": "flax_model-00001-of-00003.msgpack",
330
+ "transformer/h/7/input_layernorm/bias": "flax_model-00001-of-00003.msgpack",
331
+ "transformer/h/7/input_layernorm/scale": "flax_model-00001-of-00003.msgpack",
332
+ "transformer/h/7/mlp/dense_4h_to_h/bias": "flax_model-00002-of-00003.msgpack",
333
+ "transformer/h/7/mlp/dense_4h_to_h/kernel": "flax_model-00002-of-00003.msgpack",
334
+ "transformer/h/7/mlp/dense_h_to_4h/bias": "flax_model-00002-of-00003.msgpack",
335
+ "transformer/h/7/mlp/dense_h_to_4h/kernel": "flax_model-00002-of-00003.msgpack",
336
+ "transformer/h/7/post_attention_layernorm/bias": "flax_model-00002-of-00003.msgpack",
337
+ "transformer/h/7/post_attention_layernorm/scale": "flax_model-00002-of-00003.msgpack",
338
+ "transformer/h/7/self_attention/dense/bias": "flax_model-00002-of-00003.msgpack",
339
+ "transformer/h/7/self_attention/dense/kernel": "flax_model-00002-of-00003.msgpack",
340
+ "transformer/h/7/self_attention/query_key_value/bias": "flax_model-00001-of-00003.msgpack",
341
+ "transformer/h/7/self_attention/query_key_value/kernel": "flax_model-00001-of-00003.msgpack",
342
+ "transformer/h/8/input_layernorm/bias": "flax_model-00002-of-00003.msgpack",
343
+ "transformer/h/8/input_layernorm/scale": "flax_model-00002-of-00003.msgpack",
344
+ "transformer/h/8/mlp/dense_4h_to_h/bias": "flax_model-00002-of-00003.msgpack",
345
+ "transformer/h/8/mlp/dense_4h_to_h/kernel": "flax_model-00002-of-00003.msgpack",
346
+ "transformer/h/8/mlp/dense_h_to_4h/bias": "flax_model-00002-of-00003.msgpack",
347
+ "transformer/h/8/mlp/dense_h_to_4h/kernel": "flax_model-00002-of-00003.msgpack",
348
+ "transformer/h/8/post_attention_layernorm/bias": "flax_model-00002-of-00003.msgpack",
349
+ "transformer/h/8/post_attention_layernorm/scale": "flax_model-00002-of-00003.msgpack",
350
+ "transformer/h/8/self_attention/dense/bias": "flax_model-00002-of-00003.msgpack",
351
+ "transformer/h/8/self_attention/dense/kernel": "flax_model-00002-of-00003.msgpack",
352
+ "transformer/h/8/self_attention/query_key_value/bias": "flax_model-00002-of-00003.msgpack",
353
+ "transformer/h/8/self_attention/query_key_value/kernel": "flax_model-00002-of-00003.msgpack",
354
+ "transformer/h/9/input_layernorm/bias": "flax_model-00002-of-00003.msgpack",
355
+ "transformer/h/9/input_layernorm/scale": "flax_model-00002-of-00003.msgpack",
356
+ "transformer/h/9/mlp/dense_4h_to_h/bias": "flax_model-00002-of-00003.msgpack",
357
+ "transformer/h/9/mlp/dense_4h_to_h/kernel": "flax_model-00002-of-00003.msgpack",
358
+ "transformer/h/9/mlp/dense_h_to_4h/bias": "flax_model-00002-of-00003.msgpack",
359
+ "transformer/h/9/mlp/dense_h_to_4h/kernel": "flax_model-00002-of-00003.msgpack",
360
+ "transformer/h/9/post_attention_layernorm/bias": "flax_model-00002-of-00003.msgpack",
361
+ "transformer/h/9/post_attention_layernorm/scale": "flax_model-00002-of-00003.msgpack",
362
+ "transformer/h/9/self_attention/dense/bias": "flax_model-00002-of-00003.msgpack",
363
+ "transformer/h/9/self_attention/dense/kernel": "flax_model-00002-of-00003.msgpack",
364
+ "transformer/h/9/self_attention/query_key_value/bias": "flax_model-00002-of-00003.msgpack",
365
+ "transformer/h/9/self_attention/query_key_value/kernel": "flax_model-00002-of-00003.msgpack",
366
+ "transformer/ln_f/bias": "flax_model-00003-of-00003.msgpack",
367
+ "transformer/ln_f/scale": "flax_model-00003-of-00003.msgpack",
368
+ "transformer/word_embeddings/embedding": "flax_model-00001-of-00003.msgpack",
369
+ "transformer/word_embeddings_layernorm/bias": "flax_model-00001-of-00003.msgpack",
370
+ "transformer/word_embeddings_layernorm/scale": "flax_model-00001-of-00003.msgpack"
371
+ }
372
+ }
pytorch_model-00004-of-00006.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:dbc23231529818bd2476e352dde9076248fd6611287b6ce2efe15bec80c32160
3
- size 4833141050
 
 
 
 
pytorch_model-00005-of-00006.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:76fa66b79c0dd2549af5a23f72f37070e5277226044053674111289c47057f46
3
- size 4833141050
 
 
 
 
pytorch_model-00006-of-00006.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:fc7a07a7c311f3de8a299770c72afd872d9072022cab6267df0cf3e72e75763a
3
- size 4027617442
 
 
 
 
pytorch_model.bin.index.json DELETED
@@ -1,373 +0,0 @@
1
- {
2
- "metadata": {
3
- "total_size": 28276064256
4
- },
5
- "weight_map": {
6
- "lm_head.weight": "pytorch_model-00001-of-00006.bin",
7
- "transformer.h.0.input_layernorm.bias": "pytorch_model-00001-of-00006.bin",
8
- "transformer.h.0.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
9
- "transformer.h.0.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00006.bin",
10
- "transformer.h.0.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00006.bin",
11
- "transformer.h.0.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00006.bin",
12
- "transformer.h.0.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00006.bin",
13
- "transformer.h.0.post_attention_layernorm.bias": "pytorch_model-00001-of-00006.bin",
14
- "transformer.h.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
15
- "transformer.h.0.self_attention.dense.bias": "pytorch_model-00001-of-00006.bin",
16
- "transformer.h.0.self_attention.dense.weight": "pytorch_model-00001-of-00006.bin",
17
- "transformer.h.0.self_attention.query_key_value.bias": "pytorch_model-00001-of-00006.bin",
18
- "transformer.h.0.self_attention.query_key_value.weight": "pytorch_model-00001-of-00006.bin",
19
- "transformer.h.1.input_layernorm.bias": "pytorch_model-00001-of-00006.bin",
20
- "transformer.h.1.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
21
- "transformer.h.1.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00006.bin",
22
- "transformer.h.1.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00006.bin",
23
- "transformer.h.1.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00006.bin",
24
- "transformer.h.1.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00006.bin",
25
- "transformer.h.1.post_attention_layernorm.bias": "pytorch_model-00002-of-00006.bin",
26
- "transformer.h.1.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
27
- "transformer.h.1.self_attention.dense.bias": "pytorch_model-00002-of-00006.bin",
28
- "transformer.h.1.self_attention.dense.weight": "pytorch_model-00002-of-00006.bin",
29
- "transformer.h.1.self_attention.query_key_value.bias": "pytorch_model-00002-of-00006.bin",
30
- "transformer.h.1.self_attention.query_key_value.weight": "pytorch_model-00002-of-00006.bin",
31
- "transformer.h.10.input_layernorm.bias": "pytorch_model-00003-of-00006.bin",
32
- "transformer.h.10.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
33
- "transformer.h.10.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00006.bin",
34
- "transformer.h.10.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00006.bin",
35
- "transformer.h.10.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00006.bin",
36
- "transformer.h.10.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00006.bin",
37
- "transformer.h.10.post_attention_layernorm.bias": "pytorch_model-00003-of-00006.bin",
38
- "transformer.h.10.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
39
- "transformer.h.10.self_attention.dense.bias": "pytorch_model-00003-of-00006.bin",
40
- "transformer.h.10.self_attention.dense.weight": "pytorch_model-00003-of-00006.bin",
41
- "transformer.h.10.self_attention.query_key_value.bias": "pytorch_model-00003-of-00006.bin",
42
- "transformer.h.10.self_attention.query_key_value.weight": "pytorch_model-00003-of-00006.bin",
43
- "transformer.h.11.input_layernorm.bias": "pytorch_model-00003-of-00006.bin",
44
- "transformer.h.11.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
45
- "transformer.h.11.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00006.bin",
46
- "transformer.h.11.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00006.bin",
47
- "transformer.h.11.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00006.bin",
48
- "transformer.h.11.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00006.bin",
49
- "transformer.h.11.post_attention_layernorm.bias": "pytorch_model-00003-of-00006.bin",
50
- "transformer.h.11.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
51
- "transformer.h.11.self_attention.dense.bias": "pytorch_model-00003-of-00006.bin",
52
- "transformer.h.11.self_attention.dense.weight": "pytorch_model-00003-of-00006.bin",
53
- "transformer.h.11.self_attention.query_key_value.bias": "pytorch_model-00003-of-00006.bin",
54
- "transformer.h.11.self_attention.query_key_value.weight": "pytorch_model-00003-of-00006.bin",
55
- "transformer.h.12.input_layernorm.bias": "pytorch_model-00003-of-00006.bin",
56
- "transformer.h.12.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
57
- "transformer.h.12.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00006.bin",
58
- "transformer.h.12.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00006.bin",
59
- "transformer.h.12.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00006.bin",
60
- "transformer.h.12.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00006.bin",
61
- "transformer.h.12.post_attention_layernorm.bias": "pytorch_model-00003-of-00006.bin",
62
- "transformer.h.12.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
63
- "transformer.h.12.self_attention.dense.bias": "pytorch_model-00003-of-00006.bin",
64
- "transformer.h.12.self_attention.dense.weight": "pytorch_model-00003-of-00006.bin",
65
- "transformer.h.12.self_attention.query_key_value.bias": "pytorch_model-00003-of-00006.bin",
66
- "transformer.h.12.self_attention.query_key_value.weight": "pytorch_model-00003-of-00006.bin",
67
- "transformer.h.13.input_layernorm.bias": "pytorch_model-00003-of-00006.bin",
68
- "transformer.h.13.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
69
- "transformer.h.13.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00006.bin",
70
- "transformer.h.13.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00006.bin",
71
- "transformer.h.13.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00006.bin",
72
- "transformer.h.13.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00006.bin",
73
- "transformer.h.13.post_attention_layernorm.bias": "pytorch_model-00004-of-00006.bin",
74
- "transformer.h.13.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
75
- "transformer.h.13.self_attention.dense.bias": "pytorch_model-00004-of-00006.bin",
76
- "transformer.h.13.self_attention.dense.weight": "pytorch_model-00004-of-00006.bin",
77
- "transformer.h.13.self_attention.query_key_value.bias": "pytorch_model-00004-of-00006.bin",
78
- "transformer.h.13.self_attention.query_key_value.weight": "pytorch_model-00004-of-00006.bin",
79
- "transformer.h.14.input_layernorm.bias": "pytorch_model-00004-of-00006.bin",
80
- "transformer.h.14.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
81
- "transformer.h.14.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00006.bin",
82
- "transformer.h.14.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00006.bin",
83
- "transformer.h.14.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00006.bin",
84
- "transformer.h.14.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00006.bin",
85
- "transformer.h.14.post_attention_layernorm.bias": "pytorch_model-00004-of-00006.bin",
86
- "transformer.h.14.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
87
- "transformer.h.14.self_attention.dense.bias": "pytorch_model-00004-of-00006.bin",
88
- "transformer.h.14.self_attention.dense.weight": "pytorch_model-00004-of-00006.bin",
89
- "transformer.h.14.self_attention.query_key_value.bias": "pytorch_model-00004-of-00006.bin",
90
- "transformer.h.14.self_attention.query_key_value.weight": "pytorch_model-00004-of-00006.bin",
91
- "transformer.h.15.input_layernorm.bias": "pytorch_model-00004-of-00006.bin",
92
- "transformer.h.15.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
93
- "transformer.h.15.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00006.bin",
94
- "transformer.h.15.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00006.bin",
95
- "transformer.h.15.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00006.bin",
96
- "transformer.h.15.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00006.bin",
97
- "transformer.h.15.post_attention_layernorm.bias": "pytorch_model-00004-of-00006.bin",
98
- "transformer.h.15.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
99
- "transformer.h.15.self_attention.dense.bias": "pytorch_model-00004-of-00006.bin",
100
- "transformer.h.15.self_attention.dense.weight": "pytorch_model-00004-of-00006.bin",
101
- "transformer.h.15.self_attention.query_key_value.bias": "pytorch_model-00004-of-00006.bin",
102
- "transformer.h.15.self_attention.query_key_value.weight": "pytorch_model-00004-of-00006.bin",
103
- "transformer.h.16.input_layernorm.bias": "pytorch_model-00004-of-00006.bin",
104
- "transformer.h.16.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
105
- "transformer.h.16.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00006.bin",
106
- "transformer.h.16.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00006.bin",
107
- "transformer.h.16.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00006.bin",
108
- "transformer.h.16.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00006.bin",
109
- "transformer.h.16.post_attention_layernorm.bias": "pytorch_model-00004-of-00006.bin",
110
- "transformer.h.16.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
111
- "transformer.h.16.self_attention.dense.bias": "pytorch_model-00004-of-00006.bin",
112
- "transformer.h.16.self_attention.dense.weight": "pytorch_model-00004-of-00006.bin",
113
- "transformer.h.16.self_attention.query_key_value.bias": "pytorch_model-00004-of-00006.bin",
114
- "transformer.h.16.self_attention.query_key_value.weight": "pytorch_model-00004-of-00006.bin",
115
- "transformer.h.17.input_layernorm.bias": "pytorch_model-00004-of-00006.bin",
116
- "transformer.h.17.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
117
- "transformer.h.17.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00006.bin",
118
- "transformer.h.17.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00006.bin",
119
- "transformer.h.17.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00006.bin",
120
- "transformer.h.17.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00006.bin",
121
- "transformer.h.17.post_attention_layernorm.bias": "pytorch_model-00004-of-00006.bin",
122
- "transformer.h.17.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
123
- "transformer.h.17.self_attention.dense.bias": "pytorch_model-00004-of-00006.bin",
124
- "transformer.h.17.self_attention.dense.weight": "pytorch_model-00004-of-00006.bin",
125
- "transformer.h.17.self_attention.query_key_value.bias": "pytorch_model-00004-of-00006.bin",
126
- "transformer.h.17.self_attention.query_key_value.weight": "pytorch_model-00004-of-00006.bin",
127
- "transformer.h.18.input_layernorm.bias": "pytorch_model-00004-of-00006.bin",
128
- "transformer.h.18.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
129
- "transformer.h.18.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00006.bin",
130
- "transformer.h.18.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00006.bin",
131
- "transformer.h.18.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00006.bin",
132
- "transformer.h.18.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00006.bin",
133
- "transformer.h.18.post_attention_layernorm.bias": "pytorch_model-00004-of-00006.bin",
134
- "transformer.h.18.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
135
- "transformer.h.18.self_attention.dense.bias": "pytorch_model-00004-of-00006.bin",
136
- "transformer.h.18.self_attention.dense.weight": "pytorch_model-00004-of-00006.bin",
137
- "transformer.h.18.self_attention.query_key_value.bias": "pytorch_model-00004-of-00006.bin",
138
- "transformer.h.18.self_attention.query_key_value.weight": "pytorch_model-00004-of-00006.bin",
139
- "transformer.h.19.input_layernorm.bias": "pytorch_model-00004-of-00006.bin",
140
- "transformer.h.19.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
141
- "transformer.h.19.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00006.bin",
142
- "transformer.h.19.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00006.bin",
143
- "transformer.h.19.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00006.bin",
144
- "transformer.h.19.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00006.bin",
145
- "transformer.h.19.post_attention_layernorm.bias": "pytorch_model-00005-of-00006.bin",
146
- "transformer.h.19.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
147
- "transformer.h.19.self_attention.dense.bias": "pytorch_model-00005-of-00006.bin",
148
- "transformer.h.19.self_attention.dense.weight": "pytorch_model-00005-of-00006.bin",
149
- "transformer.h.19.self_attention.query_key_value.bias": "pytorch_model-00005-of-00006.bin",
150
- "transformer.h.19.self_attention.query_key_value.weight": "pytorch_model-00005-of-00006.bin",
151
- "transformer.h.2.input_layernorm.bias": "pytorch_model-00002-of-00006.bin",
152
- "transformer.h.2.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
153
- "transformer.h.2.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00006.bin",
154
- "transformer.h.2.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00006.bin",
155
- "transformer.h.2.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00006.bin",
156
- "transformer.h.2.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00006.bin",
157
- "transformer.h.2.post_attention_layernorm.bias": "pytorch_model-00002-of-00006.bin",
158
- "transformer.h.2.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
159
- "transformer.h.2.self_attention.dense.bias": "pytorch_model-00002-of-00006.bin",
160
- "transformer.h.2.self_attention.dense.weight": "pytorch_model-00002-of-00006.bin",
161
- "transformer.h.2.self_attention.query_key_value.bias": "pytorch_model-00002-of-00006.bin",
162
- "transformer.h.2.self_attention.query_key_value.weight": "pytorch_model-00002-of-00006.bin",
163
- "transformer.h.20.input_layernorm.bias": "pytorch_model-00005-of-00006.bin",
164
- "transformer.h.20.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
165
- "transformer.h.20.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00006.bin",
166
- "transformer.h.20.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00006.bin",
167
- "transformer.h.20.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00006.bin",
168
- "transformer.h.20.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00006.bin",
169
- "transformer.h.20.post_attention_layernorm.bias": "pytorch_model-00005-of-00006.bin",
170
- "transformer.h.20.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
171
- "transformer.h.20.self_attention.dense.bias": "pytorch_model-00005-of-00006.bin",
172
- "transformer.h.20.self_attention.dense.weight": "pytorch_model-00005-of-00006.bin",
173
- "transformer.h.20.self_attention.query_key_value.bias": "pytorch_model-00005-of-00006.bin",
174
- "transformer.h.20.self_attention.query_key_value.weight": "pytorch_model-00005-of-00006.bin",
175
- "transformer.h.21.input_layernorm.bias": "pytorch_model-00005-of-00006.bin",
176
- "transformer.h.21.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
177
- "transformer.h.21.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00006.bin",
178
- "transformer.h.21.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00006.bin",
179
- "transformer.h.21.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00006.bin",
180
- "transformer.h.21.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00006.bin",
181
- "transformer.h.21.post_attention_layernorm.bias": "pytorch_model-00005-of-00006.bin",
182
- "transformer.h.21.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
183
- "transformer.h.21.self_attention.dense.bias": "pytorch_model-00005-of-00006.bin",
184
- "transformer.h.21.self_attention.dense.weight": "pytorch_model-00005-of-00006.bin",
185
- "transformer.h.21.self_attention.query_key_value.bias": "pytorch_model-00005-of-00006.bin",
186
- "transformer.h.21.self_attention.query_key_value.weight": "pytorch_model-00005-of-00006.bin",
187
- "transformer.h.22.input_layernorm.bias": "pytorch_model-00005-of-00006.bin",
188
- "transformer.h.22.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
189
- "transformer.h.22.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00006.bin",
190
- "transformer.h.22.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00006.bin",
191
- "transformer.h.22.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00006.bin",
192
- "transformer.h.22.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00006.bin",
193
- "transformer.h.22.post_attention_layernorm.bias": "pytorch_model-00005-of-00006.bin",
194
- "transformer.h.22.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
195
- "transformer.h.22.self_attention.dense.bias": "pytorch_model-00005-of-00006.bin",
196
- "transformer.h.22.self_attention.dense.weight": "pytorch_model-00005-of-00006.bin",
197
- "transformer.h.22.self_attention.query_key_value.bias": "pytorch_model-00005-of-00006.bin",
198
- "transformer.h.22.self_attention.query_key_value.weight": "pytorch_model-00005-of-00006.bin",
199
- "transformer.h.23.input_layernorm.bias": "pytorch_model-00005-of-00006.bin",
200
- "transformer.h.23.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
201
- "transformer.h.23.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00006.bin",
202
- "transformer.h.23.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00006.bin",
203
- "transformer.h.23.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00006.bin",
204
- "transformer.h.23.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00006.bin",
205
- "transformer.h.23.post_attention_layernorm.bias": "pytorch_model-00005-of-00006.bin",
206
- "transformer.h.23.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
207
- "transformer.h.23.self_attention.dense.bias": "pytorch_model-00005-of-00006.bin",
208
- "transformer.h.23.self_attention.dense.weight": "pytorch_model-00005-of-00006.bin",
209
- "transformer.h.23.self_attention.query_key_value.bias": "pytorch_model-00005-of-00006.bin",
210
- "transformer.h.23.self_attention.query_key_value.weight": "pytorch_model-00005-of-00006.bin",
211
- "transformer.h.24.input_layernorm.bias": "pytorch_model-00005-of-00006.bin",
212
- "transformer.h.24.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
213
- "transformer.h.24.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00006.bin",
214
- "transformer.h.24.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00006.bin",
215
- "transformer.h.24.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00006.bin",
216
- "transformer.h.24.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00006.bin",
217
- "transformer.h.24.post_attention_layernorm.bias": "pytorch_model-00005-of-00006.bin",
218
- "transformer.h.24.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
219
- "transformer.h.24.self_attention.dense.bias": "pytorch_model-00005-of-00006.bin",
220
- "transformer.h.24.self_attention.dense.weight": "pytorch_model-00005-of-00006.bin",
221
- "transformer.h.24.self_attention.query_key_value.bias": "pytorch_model-00005-of-00006.bin",
222
- "transformer.h.24.self_attention.query_key_value.weight": "pytorch_model-00005-of-00006.bin",
223
- "transformer.h.25.input_layernorm.bias": "pytorch_model-00005-of-00006.bin",
224
- "transformer.h.25.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
225
- "transformer.h.25.mlp.dense_4h_to_h.bias": "pytorch_model-00006-of-00006.bin",
226
- "transformer.h.25.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00006.bin",
227
- "transformer.h.25.mlp.dense_h_to_4h.bias": "pytorch_model-00006-of-00006.bin",
228
- "transformer.h.25.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00006.bin",
229
- "transformer.h.25.post_attention_layernorm.bias": "pytorch_model-00006-of-00006.bin",
230
- "transformer.h.25.post_attention_layernorm.weight": "pytorch_model-00006-of-00006.bin",
231
- "transformer.h.25.self_attention.dense.bias": "pytorch_model-00006-of-00006.bin",
232
- "transformer.h.25.self_attention.dense.weight": "pytorch_model-00006-of-00006.bin",
233
- "transformer.h.25.self_attention.query_key_value.bias": "pytorch_model-00006-of-00006.bin",
234
- "transformer.h.25.self_attention.query_key_value.weight": "pytorch_model-00006-of-00006.bin",
235
- "transformer.h.26.input_layernorm.bias": "pytorch_model-00006-of-00006.bin",
236
- "transformer.h.26.input_layernorm.weight": "pytorch_model-00006-of-00006.bin",
237
- "transformer.h.26.mlp.dense_4h_to_h.bias": "pytorch_model-00006-of-00006.bin",
238
- "transformer.h.26.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00006.bin",
239
- "transformer.h.26.mlp.dense_h_to_4h.bias": "pytorch_model-00006-of-00006.bin",
240
- "transformer.h.26.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00006.bin",
241
- "transformer.h.26.post_attention_layernorm.bias": "pytorch_model-00006-of-00006.bin",
242
- "transformer.h.26.post_attention_layernorm.weight": "pytorch_model-00006-of-00006.bin",
243
- "transformer.h.26.self_attention.dense.bias": "pytorch_model-00006-of-00006.bin",
244
- "transformer.h.26.self_attention.dense.weight": "pytorch_model-00006-of-00006.bin",
245
- "transformer.h.26.self_attention.query_key_value.bias": "pytorch_model-00006-of-00006.bin",
246
- "transformer.h.26.self_attention.query_key_value.weight": "pytorch_model-00006-of-00006.bin",
247
- "transformer.h.27.input_layernorm.bias": "pytorch_model-00006-of-00006.bin",
248
- "transformer.h.27.input_layernorm.weight": "pytorch_model-00006-of-00006.bin",
249
- "transformer.h.27.mlp.dense_4h_to_h.bias": "pytorch_model-00006-of-00006.bin",
250
- "transformer.h.27.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00006.bin",
251
- "transformer.h.27.mlp.dense_h_to_4h.bias": "pytorch_model-00006-of-00006.bin",
252
- "transformer.h.27.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00006.bin",
253
- "transformer.h.27.post_attention_layernorm.bias": "pytorch_model-00006-of-00006.bin",
254
- "transformer.h.27.post_attention_layernorm.weight": "pytorch_model-00006-of-00006.bin",
255
- "transformer.h.27.self_attention.dense.bias": "pytorch_model-00006-of-00006.bin",
256
- "transformer.h.27.self_attention.dense.weight": "pytorch_model-00006-of-00006.bin",
257
- "transformer.h.27.self_attention.query_key_value.bias": "pytorch_model-00006-of-00006.bin",
258
- "transformer.h.27.self_attention.query_key_value.weight": "pytorch_model-00006-of-00006.bin",
259
- "transformer.h.28.input_layernorm.bias": "pytorch_model-00006-of-00006.bin",
260
- "transformer.h.28.input_layernorm.weight": "pytorch_model-00006-of-00006.bin",
261
- "transformer.h.28.mlp.dense_4h_to_h.bias": "pytorch_model-00006-of-00006.bin",
262
- "transformer.h.28.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00006.bin",
263
- "transformer.h.28.mlp.dense_h_to_4h.bias": "pytorch_model-00006-of-00006.bin",
264
- "transformer.h.28.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00006.bin",
265
- "transformer.h.28.post_attention_layernorm.bias": "pytorch_model-00006-of-00006.bin",
266
- "transformer.h.28.post_attention_layernorm.weight": "pytorch_model-00006-of-00006.bin",
267
- "transformer.h.28.self_attention.dense.bias": "pytorch_model-00006-of-00006.bin",
268
- "transformer.h.28.self_attention.dense.weight": "pytorch_model-00006-of-00006.bin",
269
- "transformer.h.28.self_attention.query_key_value.bias": "pytorch_model-00006-of-00006.bin",
270
- "transformer.h.28.self_attention.query_key_value.weight": "pytorch_model-00006-of-00006.bin",
271
- "transformer.h.29.input_layernorm.bias": "pytorch_model-00006-of-00006.bin",
272
- "transformer.h.29.input_layernorm.weight": "pytorch_model-00006-of-00006.bin",
273
- "transformer.h.29.mlp.dense_4h_to_h.bias": "pytorch_model-00006-of-00006.bin",
274
- "transformer.h.29.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00006.bin",
275
- "transformer.h.29.mlp.dense_h_to_4h.bias": "pytorch_model-00006-of-00006.bin",
276
- "transformer.h.29.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00006.bin",
277
- "transformer.h.29.post_attention_layernorm.bias": "pytorch_model-00006-of-00006.bin",
278
- "transformer.h.29.post_attention_layernorm.weight": "pytorch_model-00006-of-00006.bin",
279
- "transformer.h.29.self_attention.dense.bias": "pytorch_model-00006-of-00006.bin",
280
- "transformer.h.29.self_attention.dense.weight": "pytorch_model-00006-of-00006.bin",
281
- "transformer.h.29.self_attention.query_key_value.bias": "pytorch_model-00006-of-00006.bin",
282
- "transformer.h.29.self_attention.query_key_value.weight": "pytorch_model-00006-of-00006.bin",
283
- "transformer.h.3.input_layernorm.bias": "pytorch_model-00002-of-00006.bin",
284
- "transformer.h.3.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
285
- "transformer.h.3.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00006.bin",
286
- "transformer.h.3.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00006.bin",
287
- "transformer.h.3.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00006.bin",
288
- "transformer.h.3.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00006.bin",
289
- "transformer.h.3.post_attention_layernorm.bias": "pytorch_model-00002-of-00006.bin",
290
- "transformer.h.3.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
291
- "transformer.h.3.self_attention.dense.bias": "pytorch_model-00002-of-00006.bin",
292
- "transformer.h.3.self_attention.dense.weight": "pytorch_model-00002-of-00006.bin",
293
- "transformer.h.3.self_attention.query_key_value.bias": "pytorch_model-00002-of-00006.bin",
294
- "transformer.h.3.self_attention.query_key_value.weight": "pytorch_model-00002-of-00006.bin",
295
- "transformer.h.4.input_layernorm.bias": "pytorch_model-00002-of-00006.bin",
296
- "transformer.h.4.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
297
- "transformer.h.4.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00006.bin",
298
- "transformer.h.4.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00006.bin",
299
- "transformer.h.4.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00006.bin",
300
- "transformer.h.4.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00006.bin",
301
- "transformer.h.4.post_attention_layernorm.bias": "pytorch_model-00002-of-00006.bin",
302
- "transformer.h.4.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
303
- "transformer.h.4.self_attention.dense.bias": "pytorch_model-00002-of-00006.bin",
304
- "transformer.h.4.self_attention.dense.weight": "pytorch_model-00002-of-00006.bin",
305
- "transformer.h.4.self_attention.query_key_value.bias": "pytorch_model-00002-of-00006.bin",
306
- "transformer.h.4.self_attention.query_key_value.weight": "pytorch_model-00002-of-00006.bin",
307
- "transformer.h.5.input_layernorm.bias": "pytorch_model-00002-of-00006.bin",
308
- "transformer.h.5.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
309
- "transformer.h.5.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00006.bin",
310
- "transformer.h.5.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00006.bin",
311
- "transformer.h.5.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00006.bin",
312
- "transformer.h.5.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00006.bin",
313
- "transformer.h.5.post_attention_layernorm.bias": "pytorch_model-00002-of-00006.bin",
314
- "transformer.h.5.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
315
- "transformer.h.5.self_attention.dense.bias": "pytorch_model-00002-of-00006.bin",
316
- "transformer.h.5.self_attention.dense.weight": "pytorch_model-00002-of-00006.bin",
317
- "transformer.h.5.self_attention.query_key_value.bias": "pytorch_model-00002-of-00006.bin",
318
- "transformer.h.5.self_attention.query_key_value.weight": "pytorch_model-00002-of-00006.bin",
319
- "transformer.h.6.input_layernorm.bias": "pytorch_model-00002-of-00006.bin",
320
- "transformer.h.6.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
321
- "transformer.h.6.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00006.bin",
322
- "transformer.h.6.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00006.bin",
323
- "transformer.h.6.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00006.bin",
324
- "transformer.h.6.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00006.bin",
325
- "transformer.h.6.post_attention_layernorm.bias": "pytorch_model-00002-of-00006.bin",
326
- "transformer.h.6.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
327
- "transformer.h.6.self_attention.dense.bias": "pytorch_model-00002-of-00006.bin",
328
- "transformer.h.6.self_attention.dense.weight": "pytorch_model-00002-of-00006.bin",
329
- "transformer.h.6.self_attention.query_key_value.bias": "pytorch_model-00002-of-00006.bin",
330
- "transformer.h.6.self_attention.query_key_value.weight": "pytorch_model-00002-of-00006.bin",
331
- "transformer.h.7.input_layernorm.bias": "pytorch_model-00002-of-00006.bin",
332
- "transformer.h.7.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
333
- "transformer.h.7.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00006.bin",
334
- "transformer.h.7.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00006.bin",
335
- "transformer.h.7.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00006.bin",
336
- "transformer.h.7.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00006.bin",
337
- "transformer.h.7.post_attention_layernorm.bias": "pytorch_model-00003-of-00006.bin",
338
- "transformer.h.7.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
339
- "transformer.h.7.self_attention.dense.bias": "pytorch_model-00003-of-00006.bin",
340
- "transformer.h.7.self_attention.dense.weight": "pytorch_model-00003-of-00006.bin",
341
- "transformer.h.7.self_attention.query_key_value.bias": "pytorch_model-00003-of-00006.bin",
342
- "transformer.h.7.self_attention.query_key_value.weight": "pytorch_model-00003-of-00006.bin",
343
- "transformer.h.8.input_layernorm.bias": "pytorch_model-00003-of-00006.bin",
344
- "transformer.h.8.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
345
- "transformer.h.8.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00006.bin",
346
- "transformer.h.8.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00006.bin",
347
- "transformer.h.8.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00006.bin",
348
- "transformer.h.8.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00006.bin",
349
- "transformer.h.8.post_attention_layernorm.bias": "pytorch_model-00003-of-00006.bin",
350
- "transformer.h.8.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
351
- "transformer.h.8.self_attention.dense.bias": "pytorch_model-00003-of-00006.bin",
352
- "transformer.h.8.self_attention.dense.weight": "pytorch_model-00003-of-00006.bin",
353
- "transformer.h.8.self_attention.query_key_value.bias": "pytorch_model-00003-of-00006.bin",
354
- "transformer.h.8.self_attention.query_key_value.weight": "pytorch_model-00003-of-00006.bin",
355
- "transformer.h.9.input_layernorm.bias": "pytorch_model-00003-of-00006.bin",
356
- "transformer.h.9.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
357
- "transformer.h.9.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00006.bin",
358
- "transformer.h.9.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00006.bin",
359
- "transformer.h.9.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00006.bin",
360
- "transformer.h.9.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00006.bin",
361
- "transformer.h.9.post_attention_layernorm.bias": "pytorch_model-00003-of-00006.bin",
362
- "transformer.h.9.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
363
- "transformer.h.9.self_attention.dense.bias": "pytorch_model-00003-of-00006.bin",
364
- "transformer.h.9.self_attention.dense.weight": "pytorch_model-00003-of-00006.bin",
365
- "transformer.h.9.self_attention.query_key_value.bias": "pytorch_model-00003-of-00006.bin",
366
- "transformer.h.9.self_attention.query_key_value.weight": "pytorch_model-00003-of-00006.bin",
367
- "transformer.ln_f.bias": "pytorch_model-00006-of-00006.bin",
368
- "transformer.ln_f.weight": "pytorch_model-00006-of-00006.bin",
369
- "transformer.word_embeddings.weight": "pytorch_model-00001-of-00006.bin",
370
- "transformer.word_embeddings_layernorm.bias": "pytorch_model-00001-of-00006.bin",
371
- "transformer.word_embeddings_layernorm.weight": "pytorch_model-00001-of-00006.bin"
372
- }
373
- }