Hugging Face's logo

jiannanx
/
fisher-matrix-6B

Text Generation
Transformers
PyTorch
gptj
Inference Endpoints
Model card Files Community
jiannanx commited on
Commit
f609389
•
1 Parent(s): 9d9ce58

Upload GPTJForCausalLM

Browse files
Files changed (6) hide show
  1. config.json +42 -0
  2. generation_config.json +6 -0
  3. pytorch_model-00001-of-00003.bin +3 -0
  4. pytorch_model-00002-of-00003.bin +3 -0
  5. pytorch_model-00003-of-00003.bin +3 -0
  6. pytorch_model.bin.index.json +348 -0
config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "fisher-matrix-6B",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPTJForCausalLM"
6
+ ],
7
+ "attn_pdrop": 0.0,
8
+ "bos_token_id": 50256,
9
+ "embd_pdrop": 0.0,
10
+ "eos_token_id": 50256,
11
+ "gradient_checkpointing": false,
12
+ "initializer_range": 0.02,
13
+ "layer_norm_epsilon": 1e-05,
14
+ "model_type": "gptj",
15
+ "n_embd": 4096,
16
+ "n_head": 16,
17
+ "n_inner": null,
18
+ "n_layer": 28,
19
+ "n_positions": 2048,
20
+ "resid_pdrop": 0.0,
21
+ "rotary": true,
22
+ "rotary_dim": 64,
23
+ "scale_attn_weights": true,
24
+ "summary_activation": null,
25
+ "summary_first_dropout": 0.1,
26
+ "summary_proj_to_labels": true,
27
+ "summary_type": "cls_index",
28
+ "summary_use_proj": true,
29
+ "task_specific_params": {
30
+ "text-generation": {
31
+ "do_sample": true,
32
+ "max_length": 50,
33
+ "temperature": 1.0
34
+ }
35
+ },
36
+ "tie_word_embeddings": false,
37
+ "tokenizer_class": "GPT2Tokenizer",
38
+ "torch_dtype": "float32",
39
+ "transformers_version": "4.28.1",
40
+ "use_cache": true,
41
+ "vocab_size": 50400
42
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "eos_token_id": 50256,
5
+ "transformers_version": "4.28.1"
6
+ }
pytorch_model-00001-of-00003.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aca28a3f0ed12f8140d159758bce95ffdde2245fc63587666f5290a6973871fb
3
+ size 10004232434
pytorch_model-00002-of-00003.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c3d1a086728295ecc3f81ebcbb43fde3cd1dd2434fd03207098277414346e53
3
+ size 9983934481
pytorch_model-00003-of-00003.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a64fe8fd43ec6ce4f5e208d9e5367e77d4745d3ffb6aacca3957b284440d289f
3
+ size 4332918895
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,348 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 24218211312.0
4
+ },
5
+ "weight_map": {
6
+ "lm_head.bias": "pytorch_model-00003-of-00003.bin",
7
+ "lm_head.weight": "pytorch_model-00003-of-00003.bin",
8
+ "transformer.h.0.attn.bias": "pytorch_model-00001-of-00003.bin",
9
+ "transformer.h.0.attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
10
+ "transformer.h.0.attn.masked_bias": "pytorch_model-00001-of-00003.bin",
11
+ "transformer.h.0.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
12
+ "transformer.h.0.attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
13
+ "transformer.h.0.attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
14
+ "transformer.h.0.ln_1.bias": "pytorch_model-00001-of-00003.bin",
15
+ "transformer.h.0.ln_1.weight": "pytorch_model-00001-of-00003.bin",
16
+ "transformer.h.0.mlp.fc_in.bias": "pytorch_model-00001-of-00003.bin",
17
+ "transformer.h.0.mlp.fc_in.weight": "pytorch_model-00001-of-00003.bin",
18
+ "transformer.h.0.mlp.fc_out.bias": "pytorch_model-00001-of-00003.bin",
19
+ "transformer.h.0.mlp.fc_out.weight": "pytorch_model-00001-of-00003.bin",
20
+ "transformer.h.1.attn.bias": "pytorch_model-00001-of-00003.bin",
21
+ "transformer.h.1.attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
22
+ "transformer.h.1.attn.masked_bias": "pytorch_model-00001-of-00003.bin",
23
+ "transformer.h.1.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
24
+ "transformer.h.1.attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
25
+ "transformer.h.1.attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
26
+ "transformer.h.1.ln_1.bias": "pytorch_model-00001-of-00003.bin",
27
+ "transformer.h.1.ln_1.weight": "pytorch_model-00001-of-00003.bin",
28
+ "transformer.h.1.mlp.fc_in.bias": "pytorch_model-00001-of-00003.bin",
29
+ "transformer.h.1.mlp.fc_in.weight": "pytorch_model-00001-of-00003.bin",
30
+ "transformer.h.1.mlp.fc_out.bias": "pytorch_model-00001-of-00003.bin",
31
+ "transformer.h.1.mlp.fc_out.weight": "pytorch_model-00001-of-00003.bin",
32
+ "transformer.h.10.attn.bias": "pytorch_model-00001-of-00003.bin",
33
+ "transformer.h.10.attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
34
+ "transformer.h.10.attn.masked_bias": "pytorch_model-00001-of-00003.bin",
35
+ "transformer.h.10.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
36
+ "transformer.h.10.attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
37
+ "transformer.h.10.attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
38
+ "transformer.h.10.ln_1.bias": "pytorch_model-00001-of-00003.bin",
39
+ "transformer.h.10.ln_1.weight": "pytorch_model-00001-of-00003.bin",
40
+ "transformer.h.10.mlp.fc_in.bias": "pytorch_model-00001-of-00003.bin",
41
+ "transformer.h.10.mlp.fc_in.weight": "pytorch_model-00001-of-00003.bin",
42
+ "transformer.h.10.mlp.fc_out.bias": "pytorch_model-00001-of-00003.bin",
43
+ "transformer.h.10.mlp.fc_out.weight": "pytorch_model-00001-of-00003.bin",
44
+ "transformer.h.11.attn.bias": "pytorch_model-00001-of-00003.bin",
45
+ "transformer.h.11.attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
46
+ "transformer.h.11.attn.masked_bias": "pytorch_model-00001-of-00003.bin",
47
+ "transformer.h.11.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
48
+ "transformer.h.11.attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
49
+ "transformer.h.11.attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
50
+ "transformer.h.11.ln_1.bias": "pytorch_model-00001-of-00003.bin",
51
+ "transformer.h.11.ln_1.weight": "pytorch_model-00001-of-00003.bin",
52
+ "transformer.h.11.mlp.fc_in.bias": "pytorch_model-00002-of-00003.bin",
53
+ "transformer.h.11.mlp.fc_in.weight": "pytorch_model-00002-of-00003.bin",
54
+ "transformer.h.11.mlp.fc_out.bias": "pytorch_model-00002-of-00003.bin",
55
+ "transformer.h.11.mlp.fc_out.weight": "pytorch_model-00002-of-00003.bin",
56
+ "transformer.h.12.attn.bias": "pytorch_model-00002-of-00003.bin",
57
+ "transformer.h.12.attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
58
+ "transformer.h.12.attn.masked_bias": "pytorch_model-00002-of-00003.bin",
59
+ "transformer.h.12.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
60
+ "transformer.h.12.attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
61
+ "transformer.h.12.attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
62
+ "transformer.h.12.ln_1.bias": "pytorch_model-00002-of-00003.bin",
63
+ "transformer.h.12.ln_1.weight": "pytorch_model-00002-of-00003.bin",
64
+ "transformer.h.12.mlp.fc_in.bias": "pytorch_model-00002-of-00003.bin",
65
+ "transformer.h.12.mlp.fc_in.weight": "pytorch_model-00002-of-00003.bin",
66
+ "transformer.h.12.mlp.fc_out.bias": "pytorch_model-00002-of-00003.bin",
67
+ "transformer.h.12.mlp.fc_out.weight": "pytorch_model-00002-of-00003.bin",
68
+ "transformer.h.13.attn.bias": "pytorch_model-00002-of-00003.bin",
69
+ "transformer.h.13.attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
70
+ "transformer.h.13.attn.masked_bias": "pytorch_model-00002-of-00003.bin",
71
+ "transformer.h.13.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
72
+ "transformer.h.13.attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
73
+ "transformer.h.13.attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
74
+ "transformer.h.13.ln_1.bias": "pytorch_model-00002-of-00003.bin",
75
+ "transformer.h.13.ln_1.weight": "pytorch_model-00002-of-00003.bin",
76
+ "transformer.h.13.mlp.fc_in.bias": "pytorch_model-00002-of-00003.bin",
77
+ "transformer.h.13.mlp.fc_in.weight": "pytorch_model-00002-of-00003.bin",
78
+ "transformer.h.13.mlp.fc_out.bias": "pytorch_model-00002-of-00003.bin",
79
+ "transformer.h.13.mlp.fc_out.weight": "pytorch_model-00002-of-00003.bin",
80
+ "transformer.h.14.attn.bias": "pytorch_model-00002-of-00003.bin",
81
+ "transformer.h.14.attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
82
+ "transformer.h.14.attn.masked_bias": "pytorch_model-00002-of-00003.bin",
83
+ "transformer.h.14.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
84
+ "transformer.h.14.attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
85
+ "transformer.h.14.attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
86
+ "transformer.h.14.ln_1.bias": "pytorch_model-00002-of-00003.bin",
87
+ "transformer.h.14.ln_1.weight": "pytorch_model-00002-of-00003.bin",
88
+ "transformer.h.14.mlp.fc_in.bias": "pytorch_model-00002-of-00003.bin",
89
+ "transformer.h.14.mlp.fc_in.weight": "pytorch_model-00002-of-00003.bin",
90
+ "transformer.h.14.mlp.fc_out.bias": "pytorch_model-00002-of-00003.bin",
91
+ "transformer.h.14.mlp.fc_out.weight": "pytorch_model-00002-of-00003.bin",
92
+ "transformer.h.15.attn.bias": "pytorch_model-00002-of-00003.bin",
93
+ "transformer.h.15.attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
94
+ "transformer.h.15.attn.masked_bias": "pytorch_model-00002-of-00003.bin",
95
+ "transformer.h.15.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
96
+ "transformer.h.15.attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
97
+ "transformer.h.15.attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
98
+ "transformer.h.15.ln_1.bias": "pytorch_model-00002-of-00003.bin",
99
+ "transformer.h.15.ln_1.weight": "pytorch_model-00002-of-00003.bin",
100
+ "transformer.h.15.mlp.fc_in.bias": "pytorch_model-00002-of-00003.bin",
101
+ "transformer.h.15.mlp.fc_in.weight": "pytorch_model-00002-of-00003.bin",
102
+ "transformer.h.15.mlp.fc_out.bias": "pytorch_model-00002-of-00003.bin",
103
+ "transformer.h.15.mlp.fc_out.weight": "pytorch_model-00002-of-00003.bin",
104
+ "transformer.h.16.attn.bias": "pytorch_model-00002-of-00003.bin",
105
+ "transformer.h.16.attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
106
+ "transformer.h.16.attn.masked_bias": "pytorch_model-00002-of-00003.bin",
107
+ "transformer.h.16.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
108
+ "transformer.h.16.attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
109
+ "transformer.h.16.attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
110
+ "transformer.h.16.ln_1.bias": "pytorch_model-00002-of-00003.bin",
111
+ "transformer.h.16.ln_1.weight": "pytorch_model-00002-of-00003.bin",
112
+ "transformer.h.16.mlp.fc_in.bias": "pytorch_model-00002-of-00003.bin",
113
+ "transformer.h.16.mlp.fc_in.weight": "pytorch_model-00002-of-00003.bin",
114
+ "transformer.h.16.mlp.fc_out.bias": "pytorch_model-00002-of-00003.bin",
115
+ "transformer.h.16.mlp.fc_out.weight": "pytorch_model-00002-of-00003.bin",
116
+ "transformer.h.17.attn.bias": "pytorch_model-00002-of-00003.bin",
117
+ "transformer.h.17.attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
118
+ "transformer.h.17.attn.masked_bias": "pytorch_model-00002-of-00003.bin",
119
+ "transformer.h.17.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
120
+ "transformer.h.17.attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
121
+ "transformer.h.17.attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
122
+ "transformer.h.17.ln_1.bias": "pytorch_model-00002-of-00003.bin",
123
+ "transformer.h.17.ln_1.weight": "pytorch_model-00002-of-00003.bin",
124
+ "transformer.h.17.mlp.fc_in.bias": "pytorch_model-00002-of-00003.bin",
125
+ "transformer.h.17.mlp.fc_in.weight": "pytorch_model-00002-of-00003.bin",
126
+ "transformer.h.17.mlp.fc_out.bias": "pytorch_model-00002-of-00003.bin",
127
+ "transformer.h.17.mlp.fc_out.weight": "pytorch_model-00002-of-00003.bin",
128
+ "transformer.h.18.attn.bias": "pytorch_model-00002-of-00003.bin",
129
+ "transformer.h.18.attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
130
+ "transformer.h.18.attn.masked_bias": "pytorch_model-00002-of-00003.bin",
131
+ "transformer.h.18.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
132
+ "transformer.h.18.attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
133
+ "transformer.h.18.attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
134
+ "transformer.h.18.ln_1.bias": "pytorch_model-00002-of-00003.bin",
135
+ "transformer.h.18.ln_1.weight": "pytorch_model-00002-of-00003.bin",
136
+ "transformer.h.18.mlp.fc_in.bias": "pytorch_model-00002-of-00003.bin",
137
+ "transformer.h.18.mlp.fc_in.weight": "pytorch_model-00002-of-00003.bin",
138
+ "transformer.h.18.mlp.fc_out.bias": "pytorch_model-00002-of-00003.bin",
139
+ "transformer.h.18.mlp.fc_out.weight": "pytorch_model-00002-of-00003.bin",
140
+ "transformer.h.19.attn.bias": "pytorch_model-00002-of-00003.bin",
141
+ "transformer.h.19.attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
142
+ "transformer.h.19.attn.masked_bias": "pytorch_model-00002-of-00003.bin",
143
+ "transformer.h.19.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
144
+ "transformer.h.19.attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
145
+ "transformer.h.19.attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
146
+ "transformer.h.19.ln_1.bias": "pytorch_model-00002-of-00003.bin",
147
+ "transformer.h.19.ln_1.weight": "pytorch_model-00002-of-00003.bin",
148
+ "transformer.h.19.mlp.fc_in.bias": "pytorch_model-00002-of-00003.bin",
149
+ "transformer.h.19.mlp.fc_in.weight": "pytorch_model-00002-of-00003.bin",
150
+ "transformer.h.19.mlp.fc_out.bias": "pytorch_model-00002-of-00003.bin",
151
+ "transformer.h.19.mlp.fc_out.weight": "pytorch_model-00002-of-00003.bin",
152
+ "transformer.h.2.attn.bias": "pytorch_model-00001-of-00003.bin",
153
+ "transformer.h.2.attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
154
+ "transformer.h.2.attn.masked_bias": "pytorch_model-00001-of-00003.bin",
155
+ "transformer.h.2.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
156
+ "transformer.h.2.attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
157
+ "transformer.h.2.attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
158
+ "transformer.h.2.ln_1.bias": "pytorch_model-00001-of-00003.bin",
159
+ "transformer.h.2.ln_1.weight": "pytorch_model-00001-of-00003.bin",
160
+ "transformer.h.2.mlp.fc_in.bias": "pytorch_model-00001-of-00003.bin",
161
+ "transformer.h.2.mlp.fc_in.weight": "pytorch_model-00001-of-00003.bin",
162
+ "transformer.h.2.mlp.fc_out.bias": "pytorch_model-00001-of-00003.bin",
163
+ "transformer.h.2.mlp.fc_out.weight": "pytorch_model-00001-of-00003.bin",
164
+ "transformer.h.20.attn.bias": "pytorch_model-00002-of-00003.bin",
165
+ "transformer.h.20.attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
166
+ "transformer.h.20.attn.masked_bias": "pytorch_model-00002-of-00003.bin",
167
+ "transformer.h.20.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
168
+ "transformer.h.20.attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
169
+ "transformer.h.20.attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
170
+ "transformer.h.20.ln_1.bias": "pytorch_model-00002-of-00003.bin",
171
+ "transformer.h.20.ln_1.weight": "pytorch_model-00002-of-00003.bin",
172
+ "transformer.h.20.mlp.fc_in.bias": "pytorch_model-00002-of-00003.bin",
173
+ "transformer.h.20.mlp.fc_in.weight": "pytorch_model-00002-of-00003.bin",
174
+ "transformer.h.20.mlp.fc_out.bias": "pytorch_model-00002-of-00003.bin",
175
+ "transformer.h.20.mlp.fc_out.weight": "pytorch_model-00002-of-00003.bin",
176
+ "transformer.h.21.attn.bias": "pytorch_model-00002-of-00003.bin",
177
+ "transformer.h.21.attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
178
+ "transformer.h.21.attn.masked_bias": "pytorch_model-00002-of-00003.bin",
179
+ "transformer.h.21.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
180
+ "transformer.h.21.attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
181
+ "transformer.h.21.attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
182
+ "transformer.h.21.ln_1.bias": "pytorch_model-00002-of-00003.bin",
183
+ "transformer.h.21.ln_1.weight": "pytorch_model-00002-of-00003.bin",
184
+ "transformer.h.21.mlp.fc_in.bias": "pytorch_model-00002-of-00003.bin",
185
+ "transformer.h.21.mlp.fc_in.weight": "pytorch_model-00002-of-00003.bin",
186
+ "transformer.h.21.mlp.fc_out.bias": "pytorch_model-00002-of-00003.bin",
187
+ "transformer.h.21.mlp.fc_out.weight": "pytorch_model-00002-of-00003.bin",
188
+ "transformer.h.22.attn.bias": "pytorch_model-00002-of-00003.bin",
189
+ "transformer.h.22.attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
190
+ "transformer.h.22.attn.masked_bias": "pytorch_model-00002-of-00003.bin",
191
+ "transformer.h.22.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
192
+ "transformer.h.22.attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
193
+ "transformer.h.22.attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
194
+ "transformer.h.22.ln_1.bias": "pytorch_model-00002-of-00003.bin",
195
+ "transformer.h.22.ln_1.weight": "pytorch_model-00002-of-00003.bin",
196
+ "transformer.h.22.mlp.fc_in.bias": "pytorch_model-00002-of-00003.bin",
197
+ "transformer.h.22.mlp.fc_in.weight": "pytorch_model-00002-of-00003.bin",
198
+ "transformer.h.22.mlp.fc_out.bias": "pytorch_model-00002-of-00003.bin",
199
+ "transformer.h.22.mlp.fc_out.weight": "pytorch_model-00002-of-00003.bin",
200
+ "transformer.h.23.attn.bias": "pytorch_model-00002-of-00003.bin",
201
+ "transformer.h.23.attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
202
+ "transformer.h.23.attn.masked_bias": "pytorch_model-00002-of-00003.bin",
203
+ "transformer.h.23.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
204
+ "transformer.h.23.attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
205
+ "transformer.h.23.attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
206
+ "transformer.h.23.ln_1.bias": "pytorch_model-00002-of-00003.bin",
207
+ "transformer.h.23.ln_1.weight": "pytorch_model-00002-of-00003.bin",
208
+ "transformer.h.23.mlp.fc_in.bias": "pytorch_model-00002-of-00003.bin",
209
+ "transformer.h.23.mlp.fc_in.weight": "pytorch_model-00002-of-00003.bin",
210
+ "transformer.h.23.mlp.fc_out.bias": "pytorch_model-00003-of-00003.bin",
211
+ "transformer.h.23.mlp.fc_out.weight": "pytorch_model-00003-of-00003.bin",
212
+ "transformer.h.24.attn.bias": "pytorch_model-00003-of-00003.bin",
213
+ "transformer.h.24.attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
214
+ "transformer.h.24.attn.masked_bias": "pytorch_model-00003-of-00003.bin",
215
+ "transformer.h.24.attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
216
+ "transformer.h.24.attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
217
+ "transformer.h.24.attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
218
+ "transformer.h.24.ln_1.bias": "pytorch_model-00003-of-00003.bin",
219
+ "transformer.h.24.ln_1.weight": "pytorch_model-00003-of-00003.bin",
220
+ "transformer.h.24.mlp.fc_in.bias": "pytorch_model-00003-of-00003.bin",
221
+ "transformer.h.24.mlp.fc_in.weight": "pytorch_model-00003-of-00003.bin",
222
+ "transformer.h.24.mlp.fc_out.bias": "pytorch_model-00003-of-00003.bin",
223
+ "transformer.h.24.mlp.fc_out.weight": "pytorch_model-00003-of-00003.bin",
224
+ "transformer.h.25.attn.bias": "pytorch_model-00003-of-00003.bin",
225
+ "transformer.h.25.attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
226
+ "transformer.h.25.attn.masked_bias": "pytorch_model-00003-of-00003.bin",
227
+ "transformer.h.25.attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
228
+ "transformer.h.25.attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
229
+ "transformer.h.25.attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
230
+ "transformer.h.25.ln_1.bias": "pytorch_model-00003-of-00003.bin",
231
+ "transformer.h.25.ln_1.weight": "pytorch_model-00003-of-00003.bin",
232
+ "transformer.h.25.mlp.fc_in.bias": "pytorch_model-00003-of-00003.bin",
233
+ "transformer.h.25.mlp.fc_in.weight": "pytorch_model-00003-of-00003.bin",
234
+ "transformer.h.25.mlp.fc_out.bias": "pytorch_model-00003-of-00003.bin",
235
+ "transformer.h.25.mlp.fc_out.weight": "pytorch_model-00003-of-00003.bin",
236
+ "transformer.h.26.attn.bias": "pytorch_model-00003-of-00003.bin",
237
+ "transformer.h.26.attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
238
+ "transformer.h.26.attn.masked_bias": "pytorch_model-00003-of-00003.bin",
239
+ "transformer.h.26.attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
240
+ "transformer.h.26.attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
241
+ "transformer.h.26.attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
242
+ "transformer.h.26.ln_1.bias": "pytorch_model-00003-of-00003.bin",
243
+ "transformer.h.26.ln_1.weight": "pytorch_model-00003-of-00003.bin",
244
+ "transformer.h.26.mlp.fc_in.bias": "pytorch_model-00003-of-00003.bin",
245
+ "transformer.h.26.mlp.fc_in.weight": "pytorch_model-00003-of-00003.bin",
246
+ "transformer.h.26.mlp.fc_out.bias": "pytorch_model-00003-of-00003.bin",
247
+ "transformer.h.26.mlp.fc_out.weight": "pytorch_model-00003-of-00003.bin",
248
+ "transformer.h.27.attn.bias": "pytorch_model-00003-of-00003.bin",
249
+ "transformer.h.27.attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
250
+ "transformer.h.27.attn.masked_bias": "pytorch_model-00003-of-00003.bin",
251
+ "transformer.h.27.attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
252
+ "transformer.h.27.attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
253
+ "transformer.h.27.attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
254
+ "transformer.h.27.ln_1.bias": "pytorch_model-00003-of-00003.bin",
255
+ "transformer.h.27.ln_1.weight": "pytorch_model-00003-of-00003.bin",
256
+ "transformer.h.27.mlp.fc_in.bias": "pytorch_model-00003-of-00003.bin",
257
+ "transformer.h.27.mlp.fc_in.weight": "pytorch_model-00003-of-00003.bin",
258
+ "transformer.h.27.mlp.fc_out.bias": "pytorch_model-00003-of-00003.bin",
259
+ "transformer.h.27.mlp.fc_out.weight": "pytorch_model-00003-of-00003.bin",
260
+ "transformer.h.3.attn.bias": "pytorch_model-00001-of-00003.bin",
261
+ "transformer.h.3.attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
262
+ "transformer.h.3.attn.masked_bias": "pytorch_model-00001-of-00003.bin",
263
+ "transformer.h.3.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
264
+ "transformer.h.3.attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
265
+ "transformer.h.3.attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
266
+ "transformer.h.3.ln_1.bias": "pytorch_model-00001-of-00003.bin",
267
+ "transformer.h.3.ln_1.weight": "pytorch_model-00001-of-00003.bin",
268
+ "transformer.h.3.mlp.fc_in.bias": "pytorch_model-00001-of-00003.bin",
269
+ "transformer.h.3.mlp.fc_in.weight": "pytorch_model-00001-of-00003.bin",
270
+ "transformer.h.3.mlp.fc_out.bias": "pytorch_model-00001-of-00003.bin",
271
+ "transformer.h.3.mlp.fc_out.weight": "pytorch_model-00001-of-00003.bin",
272
+ "transformer.h.4.attn.bias": "pytorch_model-00001-of-00003.bin",
273
+ "transformer.h.4.attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
274
+ "transformer.h.4.attn.masked_bias": "pytorch_model-00001-of-00003.bin",
275
+ "transformer.h.4.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
276
+ "transformer.h.4.attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
277
+ "transformer.h.4.attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
278
+ "transformer.h.4.ln_1.bias": "pytorch_model-00001-of-00003.bin",
279
+ "transformer.h.4.ln_1.weight": "pytorch_model-00001-of-00003.bin",
280
+ "transformer.h.4.mlp.fc_in.bias": "pytorch_model-00001-of-00003.bin",
281
+ "transformer.h.4.mlp.fc_in.weight": "pytorch_model-00001-of-00003.bin",
282
+ "transformer.h.4.mlp.fc_out.bias": "pytorch_model-00001-of-00003.bin",
283
+ "transformer.h.4.mlp.fc_out.weight": "pytorch_model-00001-of-00003.bin",
284
+ "transformer.h.5.attn.bias": "pytorch_model-00001-of-00003.bin",
285
+ "transformer.h.5.attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
286
+ "transformer.h.5.attn.masked_bias": "pytorch_model-00001-of-00003.bin",
287
+ "transformer.h.5.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
288
+ "transformer.h.5.attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
289
+ "transformer.h.5.attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
290
+ "transformer.h.5.ln_1.bias": "pytorch_model-00001-of-00003.bin",
291
+ "transformer.h.5.ln_1.weight": "pytorch_model-00001-of-00003.bin",
292
+ "transformer.h.5.mlp.fc_in.bias": "pytorch_model-00001-of-00003.bin",
293
+ "transformer.h.5.mlp.fc_in.weight": "pytorch_model-00001-of-00003.bin",
294
+ "transformer.h.5.mlp.fc_out.bias": "pytorch_model-00001-of-00003.bin",
295
+ "transformer.h.5.mlp.fc_out.weight": "pytorch_model-00001-of-00003.bin",
296
+ "transformer.h.6.attn.bias": "pytorch_model-00001-of-00003.bin",
297
+ "transformer.h.6.attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
298
+ "transformer.h.6.attn.masked_bias": "pytorch_model-00001-of-00003.bin",
299
+ "transformer.h.6.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
300
+ "transformer.h.6.attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
301
+ "transformer.h.6.attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
302
+ "transformer.h.6.ln_1.bias": "pytorch_model-00001-of-00003.bin",
303
+ "transformer.h.6.ln_1.weight": "pytorch_model-00001-of-00003.bin",
304
+ "transformer.h.6.mlp.fc_in.bias": "pytorch_model-00001-of-00003.bin",
305
+ "transformer.h.6.mlp.fc_in.weight": "pytorch_model-00001-of-00003.bin",
306
+ "transformer.h.6.mlp.fc_out.bias": "pytorch_model-00001-of-00003.bin",
307
+ "transformer.h.6.mlp.fc_out.weight": "pytorch_model-00001-of-00003.bin",
308
+ "transformer.h.7.attn.bias": "pytorch_model-00001-of-00003.bin",
309
+ "transformer.h.7.attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
310
+ "transformer.h.7.attn.masked_bias": "pytorch_model-00001-of-00003.bin",
311
+ "transformer.h.7.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
312
+ "transformer.h.7.attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
313
+ "transformer.h.7.attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
314
+ "transformer.h.7.ln_1.bias": "pytorch_model-00001-of-00003.bin",
315
+ "transformer.h.7.ln_1.weight": "pytorch_model-00001-of-00003.bin",
316
+ "transformer.h.7.mlp.fc_in.bias": "pytorch_model-00001-of-00003.bin",
317
+ "transformer.h.7.mlp.fc_in.weight": "pytorch_model-00001-of-00003.bin",
318
+ "transformer.h.7.mlp.fc_out.bias": "pytorch_model-00001-of-00003.bin",
319
+ "transformer.h.7.mlp.fc_out.weight": "pytorch_model-00001-of-00003.bin",
320
+ "transformer.h.8.attn.bias": "pytorch_model-00001-of-00003.bin",
321
+ "transformer.h.8.attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
322
+ "transformer.h.8.attn.masked_bias": "pytorch_model-00001-of-00003.bin",
323
+ "transformer.h.8.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
324
+ "transformer.h.8.attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
325
+ "transformer.h.8.attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
326
+ "transformer.h.8.ln_1.bias": "pytorch_model-00001-of-00003.bin",
327
+ "transformer.h.8.ln_1.weight": "pytorch_model-00001-of-00003.bin",
328
+ "transformer.h.8.mlp.fc_in.bias": "pytorch_model-00001-of-00003.bin",
329
+ "transformer.h.8.mlp.fc_in.weight": "pytorch_model-00001-of-00003.bin",
330
+ "transformer.h.8.mlp.fc_out.bias": "pytorch_model-00001-of-00003.bin",
331
+ "transformer.h.8.mlp.fc_out.weight": "pytorch_model-00001-of-00003.bin",
332
+ "transformer.h.9.attn.bias": "pytorch_model-00001-of-00003.bin",
333
+ "transformer.h.9.attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
334
+ "transformer.h.9.attn.masked_bias": "pytorch_model-00001-of-00003.bin",
335
+ "transformer.h.9.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
336
+ "transformer.h.9.attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
337
+ "transformer.h.9.attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
338
+ "transformer.h.9.ln_1.bias": "pytorch_model-00001-of-00003.bin",
339
+ "transformer.h.9.ln_1.weight": "pytorch_model-00001-of-00003.bin",
340
+ "transformer.h.9.mlp.fc_in.bias": "pytorch_model-00001-of-00003.bin",
341
+ "transformer.h.9.mlp.fc_in.weight": "pytorch_model-00001-of-00003.bin",
342
+ "transformer.h.9.mlp.fc_out.bias": "pytorch_model-00001-of-00003.bin",
343
+ "transformer.h.9.mlp.fc_out.weight": "pytorch_model-00001-of-00003.bin",
344
+ "transformer.ln_f.bias": "pytorch_model-00003-of-00003.bin",
345
+ "transformer.ln_f.weight": "pytorch_model-00003-of-00003.bin",
346
+ "transformer.wte.weight": "pytorch_model-00001-of-00003.bin"
347
+ }
348
+ }