Hugging Face's logo

Salesforce
/
codet5p-2b

Text2Text Generation
Transformers
PyTorch
codet5p
custom_code
Model card Files Community
6
yuewang-sf commited on
Commit
2333245
•
1 Parent(s): 36e13a4

Upload model files

Browse files
Files changed (4) hide show
  1. config.json +5 -5
  2. pytorch_model-00001-of-00002.bin +3 -0
  3. pytorch_model-00002-of-00002.bin +3 -0
  4. pytorch_model.bin.index.json +498 -0
config.json CHANGED
@@ -1,10 +1,10 @@
1
  {
2
- "_name_or_path": "codet5p-2b",
3
  "architectures": [
4
  "CodeT5pEncoderDecoderModel"
5
  ],
6
  "decoder": {
7
- "_name_or_path": "codet5p-2b-decoder",
8
  "activation_function": "gelu_new",
9
  "add_cross_attention": true,
10
  "architectures": [
@@ -44,10 +44,10 @@
44
  "min_length": 0,
45
  "model_type": "codet5p_module",
46
  "n_ctx": 2048,
47
- "n_embd": 2560,
48
- "n_head": 32,
49
  "n_inner": null,
50
- "n_layer": 32,
51
  "n_positions": 2048,
52
  "no_repeat_ngram_size": 0,
53
  "num_beam_groups": 1,
 
1
  {
2
+ "_name_or_path": "codet5p-6b",
3
  "architectures": [
4
  "CodeT5pEncoderDecoderModel"
5
  ],
6
  "decoder": {
7
+ "_name_or_path": "codet5p-6b-decoder",
8
  "activation_function": "gelu_new",
9
  "add_cross_attention": true,
10
  "architectures": [
 
44
  "min_length": 0,
45
  "model_type": "codet5p_module",
46
  "n_ctx": 2048,
47
+ "n_embd": 4096,
48
+ "n_head": 16,
49
  "n_inner": null,
50
+ "n_layer": 33,
51
  "n_positions": 2048,
52
  "no_repeat_ngram_size": 0,
53
  "num_beam_groups": 1,
pytorch_model-00001-of-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4f816e805e4a596a1405788344bd2715241ee86e2de6e1dcb73f5b99e5886c8
3
+ size 7895051144
pytorch_model-00002-of-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:132c7df3b7031a8846838c6350cf687da3e51c96424e5ed6512390d75020c273
3
+ size 7211114903
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,498 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 15105998848
4
+ },
5
+ "weight_map": {
6
+ "decoder.lm_head.bias": "pytorch_model-00002-of-00002.bin",
7
+ "decoder.lm_head.weight": "pytorch_model-00002-of-00002.bin",
8
+ "decoder.transformer.h.0.attn.causal_mask": "pytorch_model-00001-of-00002.bin",
9
+ "decoder.transformer.h.0.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
10
+ "decoder.transformer.h.0.attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
11
+ "decoder.transformer.h.0.ln_1.bias": "pytorch_model-00001-of-00002.bin",
12
+ "decoder.transformer.h.0.ln_1.weight": "pytorch_model-00001-of-00002.bin",
13
+ "decoder.transformer.h.0.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
14
+ "decoder.transformer.h.0.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
15
+ "decoder.transformer.h.0.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
16
+ "decoder.transformer.h.0.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
17
+ "decoder.transformer.h.1.attn.causal_mask": "pytorch_model-00001-of-00002.bin",
18
+ "decoder.transformer.h.1.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
19
+ "decoder.transformer.h.1.attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
20
+ "decoder.transformer.h.1.ln_1.bias": "pytorch_model-00001-of-00002.bin",
21
+ "decoder.transformer.h.1.ln_1.weight": "pytorch_model-00001-of-00002.bin",
22
+ "decoder.transformer.h.1.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
23
+ "decoder.transformer.h.1.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
24
+ "decoder.transformer.h.1.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
25
+ "decoder.transformer.h.1.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
26
+ "decoder.transformer.h.10.attn.causal_mask": "pytorch_model-00001-of-00002.bin",
27
+ "decoder.transformer.h.10.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
28
+ "decoder.transformer.h.10.attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
29
+ "decoder.transformer.h.10.ln_1.bias": "pytorch_model-00001-of-00002.bin",
30
+ "decoder.transformer.h.10.ln_1.weight": "pytorch_model-00001-of-00002.bin",
31
+ "decoder.transformer.h.10.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
32
+ "decoder.transformer.h.10.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
33
+ "decoder.transformer.h.10.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
34
+ "decoder.transformer.h.10.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
35
+ "decoder.transformer.h.11.attn.causal_mask": "pytorch_model-00001-of-00002.bin",
36
+ "decoder.transformer.h.11.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
37
+ "decoder.transformer.h.11.attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
38
+ "decoder.transformer.h.11.ln_1.bias": "pytorch_model-00001-of-00002.bin",
39
+ "decoder.transformer.h.11.ln_1.weight": "pytorch_model-00001-of-00002.bin",
40
+ "decoder.transformer.h.11.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
41
+ "decoder.transformer.h.11.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
42
+ "decoder.transformer.h.11.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
43
+ "decoder.transformer.h.11.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
44
+ "decoder.transformer.h.12.attn.causal_mask": "pytorch_model-00001-of-00002.bin",
45
+ "decoder.transformer.h.12.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
46
+ "decoder.transformer.h.12.attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
47
+ "decoder.transformer.h.12.ln_1.bias": "pytorch_model-00001-of-00002.bin",
48
+ "decoder.transformer.h.12.ln_1.weight": "pytorch_model-00001-of-00002.bin",
49
+ "decoder.transformer.h.12.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
50
+ "decoder.transformer.h.12.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
51
+ "decoder.transformer.h.12.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
52
+ "decoder.transformer.h.12.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
53
+ "decoder.transformer.h.13.attn.causal_mask": "pytorch_model-00001-of-00002.bin",
54
+ "decoder.transformer.h.13.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
55
+ "decoder.transformer.h.13.attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
56
+ "decoder.transformer.h.13.ln_1.bias": "pytorch_model-00001-of-00002.bin",
57
+ "decoder.transformer.h.13.ln_1.weight": "pytorch_model-00001-of-00002.bin",
58
+ "decoder.transformer.h.13.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
59
+ "decoder.transformer.h.13.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
60
+ "decoder.transformer.h.13.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
61
+ "decoder.transformer.h.13.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
62
+ "decoder.transformer.h.14.attn.causal_mask": "pytorch_model-00001-of-00002.bin",
63
+ "decoder.transformer.h.14.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
64
+ "decoder.transformer.h.14.attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
65
+ "decoder.transformer.h.14.ln_1.bias": "pytorch_model-00001-of-00002.bin",
66
+ "decoder.transformer.h.14.ln_1.weight": "pytorch_model-00001-of-00002.bin",
67
+ "decoder.transformer.h.14.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
68
+ "decoder.transformer.h.14.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
69
+ "decoder.transformer.h.14.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
70
+ "decoder.transformer.h.14.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
71
+ "decoder.transformer.h.15.attn.causal_mask": "pytorch_model-00001-of-00002.bin",
72
+ "decoder.transformer.h.15.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
73
+ "decoder.transformer.h.15.attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
74
+ "decoder.transformer.h.15.ln_1.bias": "pytorch_model-00001-of-00002.bin",
75
+ "decoder.transformer.h.15.ln_1.weight": "pytorch_model-00001-of-00002.bin",
76
+ "decoder.transformer.h.15.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
77
+ "decoder.transformer.h.15.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
78
+ "decoder.transformer.h.15.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
79
+ "decoder.transformer.h.15.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
80
+ "decoder.transformer.h.16.attn.causal_mask": "pytorch_model-00001-of-00002.bin",
81
+ "decoder.transformer.h.16.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
82
+ "decoder.transformer.h.16.attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
83
+ "decoder.transformer.h.16.ln_1.bias": "pytorch_model-00001-of-00002.bin",
84
+ "decoder.transformer.h.16.ln_1.weight": "pytorch_model-00001-of-00002.bin",
85
+ "decoder.transformer.h.16.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
86
+ "decoder.transformer.h.16.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
87
+ "decoder.transformer.h.16.mlp.fc_out.bias": "pytorch_model-00002-of-00002.bin",
88
+ "decoder.transformer.h.16.mlp.fc_out.weight": "pytorch_model-00002-of-00002.bin",
89
+ "decoder.transformer.h.17.attn.causal_mask": "pytorch_model-00002-of-00002.bin",
90
+ "decoder.transformer.h.17.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
91
+ "decoder.transformer.h.17.attn.qkv_proj.weight": "pytorch_model-00002-of-00002.bin",
92
+ "decoder.transformer.h.17.ln_1.bias": "pytorch_model-00002-of-00002.bin",
93
+ "decoder.transformer.h.17.ln_1.weight": "pytorch_model-00002-of-00002.bin",
94
+ "decoder.transformer.h.17.mlp.fc_in.bias": "pytorch_model-00002-of-00002.bin",
95
+ "decoder.transformer.h.17.mlp.fc_in.weight": "pytorch_model-00002-of-00002.bin",
96
+ "decoder.transformer.h.17.mlp.fc_out.bias": "pytorch_model-00002-of-00002.bin",
97
+ "decoder.transformer.h.17.mlp.fc_out.weight": "pytorch_model-00002-of-00002.bin",
98
+ "decoder.transformer.h.18.attn.causal_mask": "pytorch_model-00002-of-00002.bin",
99
+ "decoder.transformer.h.18.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
100
+ "decoder.transformer.h.18.attn.qkv_proj.weight": "pytorch_model-00002-of-00002.bin",
101
+ "decoder.transformer.h.18.ln_1.bias": "pytorch_model-00002-of-00002.bin",
102
+ "decoder.transformer.h.18.ln_1.weight": "pytorch_model-00002-of-00002.bin",
103
+ "decoder.transformer.h.18.mlp.fc_in.bias": "pytorch_model-00002-of-00002.bin",
104
+ "decoder.transformer.h.18.mlp.fc_in.weight": "pytorch_model-00002-of-00002.bin",
105
+ "decoder.transformer.h.18.mlp.fc_out.bias": "pytorch_model-00002-of-00002.bin",
106
+ "decoder.transformer.h.18.mlp.fc_out.weight": "pytorch_model-00002-of-00002.bin",
107
+ "decoder.transformer.h.19.attn.causal_mask": "pytorch_model-00002-of-00002.bin",
108
+ "decoder.transformer.h.19.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
109
+ "decoder.transformer.h.19.attn.qkv_proj.weight": "pytorch_model-00002-of-00002.bin",
110
+ "decoder.transformer.h.19.ln_1.bias": "pytorch_model-00002-of-00002.bin",
111
+ "decoder.transformer.h.19.ln_1.weight": "pytorch_model-00002-of-00002.bin",
112
+ "decoder.transformer.h.19.mlp.fc_in.bias": "pytorch_model-00002-of-00002.bin",
113
+ "decoder.transformer.h.19.mlp.fc_in.weight": "pytorch_model-00002-of-00002.bin",
114
+ "decoder.transformer.h.19.mlp.fc_out.bias": "pytorch_model-00002-of-00002.bin",
115
+ "decoder.transformer.h.19.mlp.fc_out.weight": "pytorch_model-00002-of-00002.bin",
116
+ "decoder.transformer.h.2.attn.causal_mask": "pytorch_model-00001-of-00002.bin",
117
+ "decoder.transformer.h.2.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
118
+ "decoder.transformer.h.2.attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
119
+ "decoder.transformer.h.2.ln_1.bias": "pytorch_model-00001-of-00002.bin",
120
+ "decoder.transformer.h.2.ln_1.weight": "pytorch_model-00001-of-00002.bin",
121
+ "decoder.transformer.h.2.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
122
+ "decoder.transformer.h.2.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
123
+ "decoder.transformer.h.2.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
124
+ "decoder.transformer.h.2.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
125
+ "decoder.transformer.h.20.attn.causal_mask": "pytorch_model-00002-of-00002.bin",
126
+ "decoder.transformer.h.20.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
127
+ "decoder.transformer.h.20.attn.qkv_proj.weight": "pytorch_model-00002-of-00002.bin",
128
+ "decoder.transformer.h.20.ln_1.bias": "pytorch_model-00002-of-00002.bin",
129
+ "decoder.transformer.h.20.ln_1.weight": "pytorch_model-00002-of-00002.bin",
130
+ "decoder.transformer.h.20.mlp.fc_in.bias": "pytorch_model-00002-of-00002.bin",
131
+ "decoder.transformer.h.20.mlp.fc_in.weight": "pytorch_model-00002-of-00002.bin",
132
+ "decoder.transformer.h.20.mlp.fc_out.bias": "pytorch_model-00002-of-00002.bin",
133
+ "decoder.transformer.h.20.mlp.fc_out.weight": "pytorch_model-00002-of-00002.bin",
134
+ "decoder.transformer.h.21.attn.causal_mask": "pytorch_model-00002-of-00002.bin",
135
+ "decoder.transformer.h.21.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
136
+ "decoder.transformer.h.21.attn.qkv_proj.weight": "pytorch_model-00002-of-00002.bin",
137
+ "decoder.transformer.h.21.ln_1.bias": "pytorch_model-00002-of-00002.bin",
138
+ "decoder.transformer.h.21.ln_1.weight": "pytorch_model-00002-of-00002.bin",
139
+ "decoder.transformer.h.21.mlp.fc_in.bias": "pytorch_model-00002-of-00002.bin",
140
+ "decoder.transformer.h.21.mlp.fc_in.weight": "pytorch_model-00002-of-00002.bin",
141
+ "decoder.transformer.h.21.mlp.fc_out.bias": "pytorch_model-00002-of-00002.bin",
142
+ "decoder.transformer.h.21.mlp.fc_out.weight": "pytorch_model-00002-of-00002.bin",
143
+ "decoder.transformer.h.22.attn.causal_mask": "pytorch_model-00002-of-00002.bin",
144
+ "decoder.transformer.h.22.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
145
+ "decoder.transformer.h.22.attn.qkv_proj.weight": "pytorch_model-00002-of-00002.bin",
146
+ "decoder.transformer.h.22.ln_1.bias": "pytorch_model-00002-of-00002.bin",
147
+ "decoder.transformer.h.22.ln_1.weight": "pytorch_model-00002-of-00002.bin",
148
+ "decoder.transformer.h.22.mlp.fc_in.bias": "pytorch_model-00002-of-00002.bin",
149
+ "decoder.transformer.h.22.mlp.fc_in.weight": "pytorch_model-00002-of-00002.bin",
150
+ "decoder.transformer.h.22.mlp.fc_out.bias": "pytorch_model-00002-of-00002.bin",
151
+ "decoder.transformer.h.22.mlp.fc_out.weight": "pytorch_model-00002-of-00002.bin",
152
+ "decoder.transformer.h.23.attn.causal_mask": "pytorch_model-00002-of-00002.bin",
153
+ "decoder.transformer.h.23.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
154
+ "decoder.transformer.h.23.attn.qkv_proj.weight": "pytorch_model-00002-of-00002.bin",
155
+ "decoder.transformer.h.23.ln_1.bias": "pytorch_model-00002-of-00002.bin",
156
+ "decoder.transformer.h.23.ln_1.weight": "pytorch_model-00002-of-00002.bin",
157
+ "decoder.transformer.h.23.mlp.fc_in.bias": "pytorch_model-00002-of-00002.bin",
158
+ "decoder.transformer.h.23.mlp.fc_in.weight": "pytorch_model-00002-of-00002.bin",
159
+ "decoder.transformer.h.23.mlp.fc_out.bias": "pytorch_model-00002-of-00002.bin",
160
+ "decoder.transformer.h.23.mlp.fc_out.weight": "pytorch_model-00002-of-00002.bin",
161
+ "decoder.transformer.h.24.attn.causal_mask": "pytorch_model-00002-of-00002.bin",
162
+ "decoder.transformer.h.24.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
163
+ "decoder.transformer.h.24.attn.qkv_proj.weight": "pytorch_model-00002-of-00002.bin",
164
+ "decoder.transformer.h.24.ln_1.bias": "pytorch_model-00002-of-00002.bin",
165
+ "decoder.transformer.h.24.ln_1.weight": "pytorch_model-00002-of-00002.bin",
166
+ "decoder.transformer.h.24.mlp.fc_in.bias": "pytorch_model-00002-of-00002.bin",
167
+ "decoder.transformer.h.24.mlp.fc_in.weight": "pytorch_model-00002-of-00002.bin",
168
+ "decoder.transformer.h.24.mlp.fc_out.bias": "pytorch_model-00002-of-00002.bin",
169
+ "decoder.transformer.h.24.mlp.fc_out.weight": "pytorch_model-00002-of-00002.bin",
170
+ "decoder.transformer.h.25.attn.causal_mask": "pytorch_model-00002-of-00002.bin",
171
+ "decoder.transformer.h.25.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
172
+ "decoder.transformer.h.25.attn.qkv_proj.weight": "pytorch_model-00002-of-00002.bin",
173
+ "decoder.transformer.h.25.ln_1.bias": "pytorch_model-00002-of-00002.bin",
174
+ "decoder.transformer.h.25.ln_1.weight": "pytorch_model-00002-of-00002.bin",
175
+ "decoder.transformer.h.25.mlp.fc_in.bias": "pytorch_model-00002-of-00002.bin",
176
+ "decoder.transformer.h.25.mlp.fc_in.weight": "pytorch_model-00002-of-00002.bin",
177
+ "decoder.transformer.h.25.mlp.fc_out.bias": "pytorch_model-00002-of-00002.bin",
178
+ "decoder.transformer.h.25.mlp.fc_out.weight": "pytorch_model-00002-of-00002.bin",
179
+ "decoder.transformer.h.26.attn.causal_mask": "pytorch_model-00002-of-00002.bin",
180
+ "decoder.transformer.h.26.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
181
+ "decoder.transformer.h.26.attn.qkv_proj.weight": "pytorch_model-00002-of-00002.bin",
182
+ "decoder.transformer.h.26.ln_1.bias": "pytorch_model-00002-of-00002.bin",
183
+ "decoder.transformer.h.26.ln_1.weight": "pytorch_model-00002-of-00002.bin",
184
+ "decoder.transformer.h.26.mlp.fc_in.bias": "pytorch_model-00002-of-00002.bin",
185
+ "decoder.transformer.h.26.mlp.fc_in.weight": "pytorch_model-00002-of-00002.bin",
186
+ "decoder.transformer.h.26.mlp.fc_out.bias": "pytorch_model-00002-of-00002.bin",
187
+ "decoder.transformer.h.26.mlp.fc_out.weight": "pytorch_model-00002-of-00002.bin",
188
+ "decoder.transformer.h.27.attn.causal_mask": "pytorch_model-00002-of-00002.bin",
189
+ "decoder.transformer.h.27.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
190
+ "decoder.transformer.h.27.attn.qkv_proj.weight": "pytorch_model-00002-of-00002.bin",
191
+ "decoder.transformer.h.27.ln_1.bias": "pytorch_model-00002-of-00002.bin",
192
+ "decoder.transformer.h.27.ln_1.weight": "pytorch_model-00002-of-00002.bin",
193
+ "decoder.transformer.h.27.mlp.fc_in.bias": "pytorch_model-00002-of-00002.bin",
194
+ "decoder.transformer.h.27.mlp.fc_in.weight": "pytorch_model-00002-of-00002.bin",
195
+ "decoder.transformer.h.27.mlp.fc_out.bias": "pytorch_model-00002-of-00002.bin",
196
+ "decoder.transformer.h.27.mlp.fc_out.weight": "pytorch_model-00002-of-00002.bin",
197
+ "decoder.transformer.h.28.attn.causal_mask": "pytorch_model-00002-of-00002.bin",
198
+ "decoder.transformer.h.28.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
199
+ "decoder.transformer.h.28.attn.qkv_proj.weight": "pytorch_model-00002-of-00002.bin",
200
+ "decoder.transformer.h.28.ln_1.bias": "pytorch_model-00002-of-00002.bin",
201
+ "decoder.transformer.h.28.ln_1.weight": "pytorch_model-00002-of-00002.bin",
202
+ "decoder.transformer.h.28.mlp.fc_in.bias": "pytorch_model-00002-of-00002.bin",
203
+ "decoder.transformer.h.28.mlp.fc_in.weight": "pytorch_model-00002-of-00002.bin",
204
+ "decoder.transformer.h.28.mlp.fc_out.bias": "pytorch_model-00002-of-00002.bin",
205
+ "decoder.transformer.h.28.mlp.fc_out.weight": "pytorch_model-00002-of-00002.bin",
206
+ "decoder.transformer.h.29.attn.causal_mask": "pytorch_model-00002-of-00002.bin",
207
+ "decoder.transformer.h.29.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
208
+ "decoder.transformer.h.29.attn.qkv_proj.weight": "pytorch_model-00002-of-00002.bin",
209
+ "decoder.transformer.h.29.ln_1.bias": "pytorch_model-00002-of-00002.bin",
210
+ "decoder.transformer.h.29.ln_1.weight": "pytorch_model-00002-of-00002.bin",
211
+ "decoder.transformer.h.29.mlp.fc_in.bias": "pytorch_model-00002-of-00002.bin",
212
+ "decoder.transformer.h.29.mlp.fc_in.weight": "pytorch_model-00002-of-00002.bin",
213
+ "decoder.transformer.h.29.mlp.fc_out.bias": "pytorch_model-00002-of-00002.bin",
214
+ "decoder.transformer.h.29.mlp.fc_out.weight": "pytorch_model-00002-of-00002.bin",
215
+ "decoder.transformer.h.3.attn.causal_mask": "pytorch_model-00001-of-00002.bin",
216
+ "decoder.transformer.h.3.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
217
+ "decoder.transformer.h.3.attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
218
+ "decoder.transformer.h.3.ln_1.bias": "pytorch_model-00001-of-00002.bin",
219
+ "decoder.transformer.h.3.ln_1.weight": "pytorch_model-00001-of-00002.bin",
220
+ "decoder.transformer.h.3.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
221
+ "decoder.transformer.h.3.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
222
+ "decoder.transformer.h.3.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
223
+ "decoder.transformer.h.3.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
224
+ "decoder.transformer.h.30.attn.causal_mask": "pytorch_model-00002-of-00002.bin",
225
+ "decoder.transformer.h.30.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
226
+ "decoder.transformer.h.30.attn.qkv_proj.weight": "pytorch_model-00002-of-00002.bin",
227
+ "decoder.transformer.h.30.ln_1.bias": "pytorch_model-00002-of-00002.bin",
228
+ "decoder.transformer.h.30.ln_1.weight": "pytorch_model-00002-of-00002.bin",
229
+ "decoder.transformer.h.30.mlp.fc_in.bias": "pytorch_model-00002-of-00002.bin",
230
+ "decoder.transformer.h.30.mlp.fc_in.weight": "pytorch_model-00002-of-00002.bin",
231
+ "decoder.transformer.h.30.mlp.fc_out.bias": "pytorch_model-00002-of-00002.bin",
232
+ "decoder.transformer.h.30.mlp.fc_out.weight": "pytorch_model-00002-of-00002.bin",
233
+ "decoder.transformer.h.31.attn.causal_mask": "pytorch_model-00002-of-00002.bin",
234
+ "decoder.transformer.h.31.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
235
+ "decoder.transformer.h.31.attn.qkv_proj.weight": "pytorch_model-00002-of-00002.bin",
236
+ "decoder.transformer.h.31.ln_1.bias": "pytorch_model-00002-of-00002.bin",
237
+ "decoder.transformer.h.31.ln_1.weight": "pytorch_model-00002-of-00002.bin",
238
+ "decoder.transformer.h.31.mlp.fc_in.bias": "pytorch_model-00002-of-00002.bin",
239
+ "decoder.transformer.h.31.mlp.fc_in.weight": "pytorch_model-00002-of-00002.bin",
240
+ "decoder.transformer.h.31.mlp.fc_out.bias": "pytorch_model-00002-of-00002.bin",
241
+ "decoder.transformer.h.31.mlp.fc_out.weight": "pytorch_model-00002-of-00002.bin",
242
+ "decoder.transformer.h.32.attn.causal_mask": "pytorch_model-00002-of-00002.bin",
243
+ "decoder.transformer.h.32.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
244
+ "decoder.transformer.h.32.attn.qkv_proj.weight": "pytorch_model-00002-of-00002.bin",
245
+ "decoder.transformer.h.32.crossattention.causal_mask": "pytorch_model-00002-of-00002.bin",
246
+ "decoder.transformer.h.32.crossattention.out_proj.weight": "pytorch_model-00002-of-00002.bin",
247
+ "decoder.transformer.h.32.crossattention.q_attn.weight": "pytorch_model-00002-of-00002.bin",
248
+ "decoder.transformer.h.32.crossattention.qkv_proj.weight": "pytorch_model-00002-of-00002.bin",
249
+ "decoder.transformer.h.32.ln_1.bias": "pytorch_model-00002-of-00002.bin",
250
+ "decoder.transformer.h.32.ln_1.weight": "pytorch_model-00002-of-00002.bin",
251
+ "decoder.transformer.h.32.mlp.fc_in.bias": "pytorch_model-00002-of-00002.bin",
252
+ "decoder.transformer.h.32.mlp.fc_in.weight": "pytorch_model-00002-of-00002.bin",
253
+ "decoder.transformer.h.32.mlp.fc_out.bias": "pytorch_model-00002-of-00002.bin",
254
+ "decoder.transformer.h.32.mlp.fc_out.weight": "pytorch_model-00002-of-00002.bin",
255
+ "decoder.transformer.h.4.attn.causal_mask": "pytorch_model-00001-of-00002.bin",
256
+ "decoder.transformer.h.4.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
257
+ "decoder.transformer.h.4.attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
258
+ "decoder.transformer.h.4.ln_1.bias": "pytorch_model-00001-of-00002.bin",
259
+ "decoder.transformer.h.4.ln_1.weight": "pytorch_model-00001-of-00002.bin",
260
+ "decoder.transformer.h.4.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
261
+ "decoder.transformer.h.4.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
262
+ "decoder.transformer.h.4.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
263
+ "decoder.transformer.h.4.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
264
+ "decoder.transformer.h.5.attn.causal_mask": "pytorch_model-00001-of-00002.bin",
265
+ "decoder.transformer.h.5.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
266
+ "decoder.transformer.h.5.attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
267
+ "decoder.transformer.h.5.ln_1.bias": "pytorch_model-00001-of-00002.bin",
268
+ "decoder.transformer.h.5.ln_1.weight": "pytorch_model-00001-of-00002.bin",
269
+ "decoder.transformer.h.5.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
270
+ "decoder.transformer.h.5.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
271
+ "decoder.transformer.h.5.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
272
+ "decoder.transformer.h.5.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
273
+ "decoder.transformer.h.6.attn.causal_mask": "pytorch_model-00001-of-00002.bin",
274
+ "decoder.transformer.h.6.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
275
+ "decoder.transformer.h.6.attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
276
+ "decoder.transformer.h.6.ln_1.bias": "pytorch_model-00001-of-00002.bin",
277
+ "decoder.transformer.h.6.ln_1.weight": "pytorch_model-00001-of-00002.bin",
278
+ "decoder.transformer.h.6.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
279
+ "decoder.transformer.h.6.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
280
+ "decoder.transformer.h.6.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
281
+ "decoder.transformer.h.6.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
282
+ "decoder.transformer.h.7.attn.causal_mask": "pytorch_model-00001-of-00002.bin",
283
+ "decoder.transformer.h.7.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
284
+ "decoder.transformer.h.7.attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
285
+ "decoder.transformer.h.7.ln_1.bias": "pytorch_model-00001-of-00002.bin",
286
+ "decoder.transformer.h.7.ln_1.weight": "pytorch_model-00001-of-00002.bin",
287
+ "decoder.transformer.h.7.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
288
+ "decoder.transformer.h.7.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
289
+ "decoder.transformer.h.7.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
290
+ "decoder.transformer.h.7.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
291
+ "decoder.transformer.h.8.attn.causal_mask": "pytorch_model-00001-of-00002.bin",
292
+ "decoder.transformer.h.8.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
293
+ "decoder.transformer.h.8.attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
294
+ "decoder.transformer.h.8.ln_1.bias": "pytorch_model-00001-of-00002.bin",
295
+ "decoder.transformer.h.8.ln_1.weight": "pytorch_model-00001-of-00002.bin",
296
+ "decoder.transformer.h.8.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
297
+ "decoder.transformer.h.8.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
298
+ "decoder.transformer.h.8.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
299
+ "decoder.transformer.h.8.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
300
+ "decoder.transformer.h.9.attn.causal_mask": "pytorch_model-00001-of-00002.bin",
301
+ "decoder.transformer.h.9.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
302
+ "decoder.transformer.h.9.attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
303
+ "decoder.transformer.h.9.ln_1.bias": "pytorch_model-00001-of-00002.bin",
304
+ "decoder.transformer.h.9.ln_1.weight": "pytorch_model-00001-of-00002.bin",
305
+ "decoder.transformer.h.9.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
306
+ "decoder.transformer.h.9.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
307
+ "decoder.transformer.h.9.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
308
+ "decoder.transformer.h.9.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
309
+ "decoder.transformer.ln_f.bias": "pytorch_model-00002-of-00002.bin",
310
+ "decoder.transformer.ln_f.weight": "pytorch_model-00002-of-00002.bin",
311
+ "decoder.transformer.wte.weight": "pytorch_model-00001-of-00002.bin",
312
+ "enc_to_dec_proj.bias": "pytorch_model-00002-of-00002.bin",
313
+ "enc_to_dec_proj.weight": "pytorch_model-00002-of-00002.bin",
314
+ "encoder.h.0.attn.causal_mask": "pytorch_model-00001-of-00002.bin",
315
+ "encoder.h.0.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
316
+ "encoder.h.0.attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
317
+ "encoder.h.0.ln_1.bias": "pytorch_model-00001-of-00002.bin",
318
+ "encoder.h.0.ln_1.weight": "pytorch_model-00001-of-00002.bin",
319
+ "encoder.h.0.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
320
+ "encoder.h.0.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
321
+ "encoder.h.0.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
322
+ "encoder.h.0.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
323
+ "encoder.h.1.attn.causal_mask": "pytorch_model-00001-of-00002.bin",
324
+ "encoder.h.1.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
325
+ "encoder.h.1.attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
326
+ "encoder.h.1.ln_1.bias": "pytorch_model-00001-of-00002.bin",
327
+ "encoder.h.1.ln_1.weight": "pytorch_model-00001-of-00002.bin",
328
+ "encoder.h.1.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
329
+ "encoder.h.1.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
330
+ "encoder.h.1.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
331
+ "encoder.h.1.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
332
+ "encoder.h.10.attn.causal_mask": "pytorch_model-00001-of-00002.bin",
333
+ "encoder.h.10.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
334
+ "encoder.h.10.attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
335
+ "encoder.h.10.ln_1.bias": "pytorch_model-00001-of-00002.bin",
336
+ "encoder.h.10.ln_1.weight": "pytorch_model-00001-of-00002.bin",
337
+ "encoder.h.10.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
338
+ "encoder.h.10.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
339
+ "encoder.h.10.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
340
+ "encoder.h.10.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
341
+ "encoder.h.11.attn.causal_mask": "pytorch_model-00001-of-00002.bin",
342
+ "encoder.h.11.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
343
+ "encoder.h.11.attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
344
+ "encoder.h.11.ln_1.bias": "pytorch_model-00001-of-00002.bin",
345
+ "encoder.h.11.ln_1.weight": "pytorch_model-00001-of-00002.bin",
346
+ "encoder.h.11.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
347
+ "encoder.h.11.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
348
+ "encoder.h.11.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
349
+ "encoder.h.11.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
350
+ "encoder.h.12.attn.causal_mask": "pytorch_model-00001-of-00002.bin",
351
+ "encoder.h.12.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
352
+ "encoder.h.12.attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
353
+ "encoder.h.12.ln_1.bias": "pytorch_model-00001-of-00002.bin",
354
+ "encoder.h.12.ln_1.weight": "pytorch_model-00001-of-00002.bin",
355
+ "encoder.h.12.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
356
+ "encoder.h.12.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
357
+ "encoder.h.12.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
358
+ "encoder.h.12.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
359
+ "encoder.h.13.attn.causal_mask": "pytorch_model-00001-of-00002.bin",
360
+ "encoder.h.13.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
361
+ "encoder.h.13.attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
362
+ "encoder.h.13.ln_1.bias": "pytorch_model-00001-of-00002.bin",
363
+ "encoder.h.13.ln_1.weight": "pytorch_model-00001-of-00002.bin",
364
+ "encoder.h.13.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
365
+ "encoder.h.13.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
366
+ "encoder.h.13.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
367
+ "encoder.h.13.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
368
+ "encoder.h.14.attn.causal_mask": "pytorch_model-00001-of-00002.bin",
369
+ "encoder.h.14.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
370
+ "encoder.h.14.attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
371
+ "encoder.h.14.ln_1.bias": "pytorch_model-00001-of-00002.bin",
372
+ "encoder.h.14.ln_1.weight": "pytorch_model-00001-of-00002.bin",
373
+ "encoder.h.14.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
374
+ "encoder.h.14.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
375
+ "encoder.h.14.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
376
+ "encoder.h.14.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
377
+ "encoder.h.15.attn.causal_mask": "pytorch_model-00001-of-00002.bin",
378
+ "encoder.h.15.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
379
+ "encoder.h.15.attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
380
+ "encoder.h.15.ln_1.bias": "pytorch_model-00001-of-00002.bin",
381
+ "encoder.h.15.ln_1.weight": "pytorch_model-00001-of-00002.bin",
382
+ "encoder.h.15.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
383
+ "encoder.h.15.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
384
+ "encoder.h.15.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
385
+ "encoder.h.15.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
386
+ "encoder.h.16.attn.causal_mask": "pytorch_model-00001-of-00002.bin",
387
+ "encoder.h.16.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
388
+ "encoder.h.16.attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
389
+ "encoder.h.16.ln_1.bias": "pytorch_model-00001-of-00002.bin",
390
+ "encoder.h.16.ln_1.weight": "pytorch_model-00001-of-00002.bin",
391
+ "encoder.h.16.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
392
+ "encoder.h.16.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
393
+ "encoder.h.16.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
394
+ "encoder.h.16.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
395
+ "encoder.h.17.attn.causal_mask": "pytorch_model-00001-of-00002.bin",
396
+ "encoder.h.17.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
397
+ "encoder.h.17.attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
398
+ "encoder.h.17.ln_1.bias": "pytorch_model-00001-of-00002.bin",
399
+ "encoder.h.17.ln_1.weight": "pytorch_model-00001-of-00002.bin",
400
+ "encoder.h.17.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
401
+ "encoder.h.17.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
402
+ "encoder.h.17.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
403
+ "encoder.h.17.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
404
+ "encoder.h.18.attn.causal_mask": "pytorch_model-00001-of-00002.bin",
405
+ "encoder.h.18.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
406
+ "encoder.h.18.attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
407
+ "encoder.h.18.ln_1.bias": "pytorch_model-00001-of-00002.bin",
408
+ "encoder.h.18.ln_1.weight": "pytorch_model-00001-of-00002.bin",
409
+ "encoder.h.18.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
410
+ "encoder.h.18.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
411
+ "encoder.h.18.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
412
+ "encoder.h.18.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
413
+ "encoder.h.19.attn.causal_mask": "pytorch_model-00001-of-00002.bin",
414
+ "encoder.h.19.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
415
+ "encoder.h.19.attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
416
+ "encoder.h.19.ln_1.bias": "pytorch_model-00001-of-00002.bin",
417
+ "encoder.h.19.ln_1.weight": "pytorch_model-00001-of-00002.bin",
418
+ "encoder.h.19.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
419
+ "encoder.h.19.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
420
+ "encoder.h.19.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
421
+ "encoder.h.19.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
422
+ "encoder.h.2.attn.causal_mask": "pytorch_model-00001-of-00002.bin",
423
+ "encoder.h.2.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
424
+ "encoder.h.2.attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
425
+ "encoder.h.2.ln_1.bias": "pytorch_model-00001-of-00002.bin",
426
+ "encoder.h.2.ln_1.weight": "pytorch_model-00001-of-00002.bin",
427
+ "encoder.h.2.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
428
+ "encoder.h.2.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
429
+ "encoder.h.2.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
430
+ "encoder.h.2.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
431
+ "encoder.h.3.attn.causal_mask": "pytorch_model-00001-of-00002.bin",
432
+ "encoder.h.3.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
433
+ "encoder.h.3.attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
434
+ "encoder.h.3.ln_1.bias": "pytorch_model-00001-of-00002.bin",
435
+ "encoder.h.3.ln_1.weight": "pytorch_model-00001-of-00002.bin",
436
+ "encoder.h.3.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
437
+ "encoder.h.3.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
438
+ "encoder.h.3.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
439
+ "encoder.h.3.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
440
+ "encoder.h.4.attn.causal_mask": "pytorch_model-00001-of-00002.bin",
441
+ "encoder.h.4.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
442
+ "encoder.h.4.attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
443
+ "encoder.h.4.ln_1.bias": "pytorch_model-00001-of-00002.bin",
444
+ "encoder.h.4.ln_1.weight": "pytorch_model-00001-of-00002.bin",
445
+ "encoder.h.4.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
446
+ "encoder.h.4.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
447
+ "encoder.h.4.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
448
+ "encoder.h.4.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
449
+ "encoder.h.5.attn.causal_mask": "pytorch_model-00001-of-00002.bin",
450
+ "encoder.h.5.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
451
+ "encoder.h.5.attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
452
+ "encoder.h.5.ln_1.bias": "pytorch_model-00001-of-00002.bin",
453
+ "encoder.h.5.ln_1.weight": "pytorch_model-00001-of-00002.bin",
454
+ "encoder.h.5.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
455
+ "encoder.h.5.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
456
+ "encoder.h.5.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
457
+ "encoder.h.5.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
458
+ "encoder.h.6.attn.causal_mask": "pytorch_model-00001-of-00002.bin",
459
+ "encoder.h.6.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
460
+ "encoder.h.6.attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
461
+ "encoder.h.6.ln_1.bias": "pytorch_model-00001-of-00002.bin",
462
+ "encoder.h.6.ln_1.weight": "pytorch_model-00001-of-00002.bin",
463
+ "encoder.h.6.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
464
+ "encoder.h.6.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
465
+ "encoder.h.6.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
466
+ "encoder.h.6.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
467
+ "encoder.h.7.attn.causal_mask": "pytorch_model-00001-of-00002.bin",
468
+ "encoder.h.7.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
469
+ "encoder.h.7.attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
470
+ "encoder.h.7.ln_1.bias": "pytorch_model-00001-of-00002.bin",
471
+ "encoder.h.7.ln_1.weight": "pytorch_model-00001-of-00002.bin",
472
+ "encoder.h.7.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
473
+ "encoder.h.7.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
474
+ "encoder.h.7.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
475
+ "encoder.h.7.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
476
+ "encoder.h.8.attn.causal_mask": "pytorch_model-00001-of-00002.bin",
477
+ "encoder.h.8.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
478
+ "encoder.h.8.attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
479
+ "encoder.h.8.ln_1.bias": "pytorch_model-00001-of-00002.bin",
480
+ "encoder.h.8.ln_1.weight": "pytorch_model-00001-of-00002.bin",
481
+ "encoder.h.8.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
482
+ "encoder.h.8.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
483
+ "encoder.h.8.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
484
+ "encoder.h.8.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
485
+ "encoder.h.9.attn.causal_mask": "pytorch_model-00001-of-00002.bin",
486
+ "encoder.h.9.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
487
+ "encoder.h.9.attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
488
+ "encoder.h.9.ln_1.bias": "pytorch_model-00001-of-00002.bin",
489
+ "encoder.h.9.ln_1.weight": "pytorch_model-00001-of-00002.bin",
490
+ "encoder.h.9.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
491
+ "encoder.h.9.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
492
+ "encoder.h.9.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
493
+ "encoder.h.9.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
494
+ "encoder.ln_f.bias": "pytorch_model-00001-of-00002.bin",
495
+ "encoder.ln_f.weight": "pytorch_model-00001-of-00002.bin",
496
+ "encoder.wte.weight": "pytorch_model-00001-of-00002.bin"
497
+ }
498
+ }