Lyaaaaaaaaaaaaaaa commited on
Commit
d7e09d4
·
1 Parent(s): b199fab

Upload 12 files

Browse files
config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "gpt2",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPT2LMHeadModel"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 50256,
9
+ "embd_pdrop": 0.1,
10
+ "eos_token_id": 50256,
11
+ "initializer_range": 0.02,
12
+ "layer_norm_epsilon": 1e-05,
13
+ "model_type": "gpt2",
14
+ "n_ctx": 1024,
15
+ "n_embd": 768,
16
+ "n_head": 12,
17
+ "n_inner": null,
18
+ "n_layer": 12,
19
+ "n_positions": 1024,
20
+ "reorder_and_upcast_attn": false,
21
+ "resid_pdrop": 0.1,
22
+ "scale_attn_by_inverse_layer_idx": false,
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
+ }
34
+ },
35
+ "torch_dtype": "float32",
36
+ "transformers_version": "4.27.4",
37
+ "use_cache": true,
38
+ "vocab_size": 50257
39
+ }
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": "4.27.4"
6
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model-00001-of-00004.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72f0270a64c1db2895076e341a6545f437ed4ed89148bb79aeb90f56fda4039c
3
+ size 197454371
pytorch_model-00002-of-00004.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:603988df77365a5d9fc1408f0b609662e65f10c348a35563c4e2cb3cc502e9ba
3
+ size 205833587
pytorch_model-00003-of-00004.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3874d750da5d09a9e9bd7f3a71b73a3f849102f5a09a0d54b29b28e8d24fa278
3
+ size 107112239
pytorch_model-00004-of-00004.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab55d9cd33e2fc716f5b3ed12680e99f48586a740e8d8c816599b611a19d17ab
3
+ size 154390442
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,180 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 653721648.0
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "pytorch_model-00004-of-00004.bin",
7
+ "transformer.h.0.attn.bias": "pytorch_model-00001-of-00004.bin",
8
+ "transformer.h.0.attn.c_attn.bias": "pytorch_model-00001-of-00004.bin",
9
+ "transformer.h.0.attn.c_attn.weight": "pytorch_model-00001-of-00004.bin",
10
+ "transformer.h.0.attn.c_proj.bias": "pytorch_model-00001-of-00004.bin",
11
+ "transformer.h.0.attn.c_proj.weight": "pytorch_model-00001-of-00004.bin",
12
+ "transformer.h.0.attn.masked_bias": "pytorch_model-00001-of-00004.bin",
13
+ "transformer.h.0.ln_1.bias": "pytorch_model-00001-of-00004.bin",
14
+ "transformer.h.0.ln_1.weight": "pytorch_model-00001-of-00004.bin",
15
+ "transformer.h.0.ln_2.bias": "pytorch_model-00001-of-00004.bin",
16
+ "transformer.h.0.ln_2.weight": "pytorch_model-00001-of-00004.bin",
17
+ "transformer.h.0.mlp.c_fc.bias": "pytorch_model-00001-of-00004.bin",
18
+ "transformer.h.0.mlp.c_fc.weight": "pytorch_model-00001-of-00004.bin",
19
+ "transformer.h.0.mlp.c_proj.bias": "pytorch_model-00001-of-00004.bin",
20
+ "transformer.h.0.mlp.c_proj.weight": "pytorch_model-00001-of-00004.bin",
21
+ "transformer.h.1.attn.bias": "pytorch_model-00001-of-00004.bin",
22
+ "transformer.h.1.attn.c_attn.bias": "pytorch_model-00001-of-00004.bin",
23
+ "transformer.h.1.attn.c_attn.weight": "pytorch_model-00001-of-00004.bin",
24
+ "transformer.h.1.attn.c_proj.bias": "pytorch_model-00001-of-00004.bin",
25
+ "transformer.h.1.attn.c_proj.weight": "pytorch_model-00001-of-00004.bin",
26
+ "transformer.h.1.attn.masked_bias": "pytorch_model-00001-of-00004.bin",
27
+ "transformer.h.1.ln_1.bias": "pytorch_model-00001-of-00004.bin",
28
+ "transformer.h.1.ln_1.weight": "pytorch_model-00001-of-00004.bin",
29
+ "transformer.h.1.ln_2.bias": "pytorch_model-00001-of-00004.bin",
30
+ "transformer.h.1.ln_2.weight": "pytorch_model-00001-of-00004.bin",
31
+ "transformer.h.1.mlp.c_fc.bias": "pytorch_model-00002-of-00004.bin",
32
+ "transformer.h.1.mlp.c_fc.weight": "pytorch_model-00002-of-00004.bin",
33
+ "transformer.h.1.mlp.c_proj.bias": "pytorch_model-00002-of-00004.bin",
34
+ "transformer.h.1.mlp.c_proj.weight": "pytorch_model-00002-of-00004.bin",
35
+ "transformer.h.10.attn.bias": "pytorch_model-00003-of-00004.bin",
36
+ "transformer.h.10.attn.c_attn.bias": "pytorch_model-00003-of-00004.bin",
37
+ "transformer.h.10.attn.c_attn.weight": "pytorch_model-00003-of-00004.bin",
38
+ "transformer.h.10.attn.c_proj.bias": "pytorch_model-00003-of-00004.bin",
39
+ "transformer.h.10.attn.c_proj.weight": "pytorch_model-00003-of-00004.bin",
40
+ "transformer.h.10.attn.masked_bias": "pytorch_model-00003-of-00004.bin",
41
+ "transformer.h.10.ln_1.bias": "pytorch_model-00003-of-00004.bin",
42
+ "transformer.h.10.ln_1.weight": "pytorch_model-00003-of-00004.bin",
43
+ "transformer.h.10.ln_2.bias": "pytorch_model-00003-of-00004.bin",
44
+ "transformer.h.10.ln_2.weight": "pytorch_model-00003-of-00004.bin",
45
+ "transformer.h.10.mlp.c_fc.bias": "pytorch_model-00003-of-00004.bin",
46
+ "transformer.h.10.mlp.c_fc.weight": "pytorch_model-00003-of-00004.bin",
47
+ "transformer.h.10.mlp.c_proj.bias": "pytorch_model-00003-of-00004.bin",
48
+ "transformer.h.10.mlp.c_proj.weight": "pytorch_model-00003-of-00004.bin",
49
+ "transformer.h.11.attn.bias": "pytorch_model-00003-of-00004.bin",
50
+ "transformer.h.11.attn.c_attn.bias": "pytorch_model-00003-of-00004.bin",
51
+ "transformer.h.11.attn.c_attn.weight": "pytorch_model-00003-of-00004.bin",
52
+ "transformer.h.11.attn.c_proj.bias": "pytorch_model-00003-of-00004.bin",
53
+ "transformer.h.11.attn.c_proj.weight": "pytorch_model-00003-of-00004.bin",
54
+ "transformer.h.11.attn.masked_bias": "pytorch_model-00003-of-00004.bin",
55
+ "transformer.h.11.ln_1.bias": "pytorch_model-00003-of-00004.bin",
56
+ "transformer.h.11.ln_1.weight": "pytorch_model-00003-of-00004.bin",
57
+ "transformer.h.11.ln_2.bias": "pytorch_model-00003-of-00004.bin",
58
+ "transformer.h.11.ln_2.weight": "pytorch_model-00003-of-00004.bin",
59
+ "transformer.h.11.mlp.c_fc.bias": "pytorch_model-00003-of-00004.bin",
60
+ "transformer.h.11.mlp.c_fc.weight": "pytorch_model-00003-of-00004.bin",
61
+ "transformer.h.11.mlp.c_proj.bias": "pytorch_model-00003-of-00004.bin",
62
+ "transformer.h.11.mlp.c_proj.weight": "pytorch_model-00003-of-00004.bin",
63
+ "transformer.h.2.attn.bias": "pytorch_model-00002-of-00004.bin",
64
+ "transformer.h.2.attn.c_attn.bias": "pytorch_model-00002-of-00004.bin",
65
+ "transformer.h.2.attn.c_attn.weight": "pytorch_model-00002-of-00004.bin",
66
+ "transformer.h.2.attn.c_proj.bias": "pytorch_model-00002-of-00004.bin",
67
+ "transformer.h.2.attn.c_proj.weight": "pytorch_model-00002-of-00004.bin",
68
+ "transformer.h.2.attn.masked_bias": "pytorch_model-00002-of-00004.bin",
69
+ "transformer.h.2.ln_1.bias": "pytorch_model-00002-of-00004.bin",
70
+ "transformer.h.2.ln_1.weight": "pytorch_model-00002-of-00004.bin",
71
+ "transformer.h.2.ln_2.bias": "pytorch_model-00002-of-00004.bin",
72
+ "transformer.h.2.ln_2.weight": "pytorch_model-00002-of-00004.bin",
73
+ "transformer.h.2.mlp.c_fc.bias": "pytorch_model-00002-of-00004.bin",
74
+ "transformer.h.2.mlp.c_fc.weight": "pytorch_model-00002-of-00004.bin",
75
+ "transformer.h.2.mlp.c_proj.bias": "pytorch_model-00002-of-00004.bin",
76
+ "transformer.h.2.mlp.c_proj.weight": "pytorch_model-00002-of-00004.bin",
77
+ "transformer.h.3.attn.bias": "pytorch_model-00002-of-00004.bin",
78
+ "transformer.h.3.attn.c_attn.bias": "pytorch_model-00002-of-00004.bin",
79
+ "transformer.h.3.attn.c_attn.weight": "pytorch_model-00002-of-00004.bin",
80
+ "transformer.h.3.attn.c_proj.bias": "pytorch_model-00002-of-00004.bin",
81
+ "transformer.h.3.attn.c_proj.weight": "pytorch_model-00002-of-00004.bin",
82
+ "transformer.h.3.attn.masked_bias": "pytorch_model-00002-of-00004.bin",
83
+ "transformer.h.3.ln_1.bias": "pytorch_model-00002-of-00004.bin",
84
+ "transformer.h.3.ln_1.weight": "pytorch_model-00002-of-00004.bin",
85
+ "transformer.h.3.ln_2.bias": "pytorch_model-00002-of-00004.bin",
86
+ "transformer.h.3.ln_2.weight": "pytorch_model-00002-of-00004.bin",
87
+ "transformer.h.3.mlp.c_fc.bias": "pytorch_model-00002-of-00004.bin",
88
+ "transformer.h.3.mlp.c_fc.weight": "pytorch_model-00002-of-00004.bin",
89
+ "transformer.h.3.mlp.c_proj.bias": "pytorch_model-00002-of-00004.bin",
90
+ "transformer.h.3.mlp.c_proj.weight": "pytorch_model-00002-of-00004.bin",
91
+ "transformer.h.4.attn.bias": "pytorch_model-00002-of-00004.bin",
92
+ "transformer.h.4.attn.c_attn.bias": "pytorch_model-00002-of-00004.bin",
93
+ "transformer.h.4.attn.c_attn.weight": "pytorch_model-00002-of-00004.bin",
94
+ "transformer.h.4.attn.c_proj.bias": "pytorch_model-00002-of-00004.bin",
95
+ "transformer.h.4.attn.c_proj.weight": "pytorch_model-00002-of-00004.bin",
96
+ "transformer.h.4.attn.masked_bias": "pytorch_model-00002-of-00004.bin",
97
+ "transformer.h.4.ln_1.bias": "pytorch_model-00002-of-00004.bin",
98
+ "transformer.h.4.ln_1.weight": "pytorch_model-00002-of-00004.bin",
99
+ "transformer.h.4.ln_2.bias": "pytorch_model-00002-of-00004.bin",
100
+ "transformer.h.4.ln_2.weight": "pytorch_model-00002-of-00004.bin",
101
+ "transformer.h.4.mlp.c_fc.bias": "pytorch_model-00002-of-00004.bin",
102
+ "transformer.h.4.mlp.c_fc.weight": "pytorch_model-00002-of-00004.bin",
103
+ "transformer.h.4.mlp.c_proj.bias": "pytorch_model-00002-of-00004.bin",
104
+ "transformer.h.4.mlp.c_proj.weight": "pytorch_model-00002-of-00004.bin",
105
+ "transformer.h.5.attn.bias": "pytorch_model-00002-of-00004.bin",
106
+ "transformer.h.5.attn.c_attn.bias": "pytorch_model-00002-of-00004.bin",
107
+ "transformer.h.5.attn.c_attn.weight": "pytorch_model-00002-of-00004.bin",
108
+ "transformer.h.5.attn.c_proj.bias": "pytorch_model-00002-of-00004.bin",
109
+ "transformer.h.5.attn.c_proj.weight": "pytorch_model-00002-of-00004.bin",
110
+ "transformer.h.5.attn.masked_bias": "pytorch_model-00002-of-00004.bin",
111
+ "transformer.h.5.ln_1.bias": "pytorch_model-00002-of-00004.bin",
112
+ "transformer.h.5.ln_1.weight": "pytorch_model-00002-of-00004.bin",
113
+ "transformer.h.5.ln_2.bias": "pytorch_model-00002-of-00004.bin",
114
+ "transformer.h.5.ln_2.weight": "pytorch_model-00002-of-00004.bin",
115
+ "transformer.h.5.mlp.c_fc.bias": "pytorch_model-00002-of-00004.bin",
116
+ "transformer.h.5.mlp.c_fc.weight": "pytorch_model-00002-of-00004.bin",
117
+ "transformer.h.5.mlp.c_proj.bias": "pytorch_model-00002-of-00004.bin",
118
+ "transformer.h.5.mlp.c_proj.weight": "pytorch_model-00002-of-00004.bin",
119
+ "transformer.h.6.attn.bias": "pytorch_model-00002-of-00004.bin",
120
+ "transformer.h.6.attn.c_attn.bias": "pytorch_model-00002-of-00004.bin",
121
+ "transformer.h.6.attn.c_attn.weight": "pytorch_model-00002-of-00004.bin",
122
+ "transformer.h.6.attn.c_proj.bias": "pytorch_model-00002-of-00004.bin",
123
+ "transformer.h.6.attn.c_proj.weight": "pytorch_model-00002-of-00004.bin",
124
+ "transformer.h.6.attn.masked_bias": "pytorch_model-00002-of-00004.bin",
125
+ "transformer.h.6.ln_1.bias": "pytorch_model-00002-of-00004.bin",
126
+ "transformer.h.6.ln_1.weight": "pytorch_model-00002-of-00004.bin",
127
+ "transformer.h.6.ln_2.bias": "pytorch_model-00002-of-00004.bin",
128
+ "transformer.h.6.ln_2.weight": "pytorch_model-00002-of-00004.bin",
129
+ "transformer.h.6.mlp.c_fc.bias": "pytorch_model-00002-of-00004.bin",
130
+ "transformer.h.6.mlp.c_fc.weight": "pytorch_model-00002-of-00004.bin",
131
+ "transformer.h.6.mlp.c_proj.bias": "pytorch_model-00002-of-00004.bin",
132
+ "transformer.h.6.mlp.c_proj.weight": "pytorch_model-00002-of-00004.bin",
133
+ "transformer.h.7.attn.bias": "pytorch_model-00002-of-00004.bin",
134
+ "transformer.h.7.attn.c_attn.bias": "pytorch_model-00002-of-00004.bin",
135
+ "transformer.h.7.attn.c_attn.weight": "pytorch_model-00002-of-00004.bin",
136
+ "transformer.h.7.attn.c_proj.bias": "pytorch_model-00002-of-00004.bin",
137
+ "transformer.h.7.attn.c_proj.weight": "pytorch_model-00002-of-00004.bin",
138
+ "transformer.h.7.attn.masked_bias": "pytorch_model-00002-of-00004.bin",
139
+ "transformer.h.7.ln_1.bias": "pytorch_model-00002-of-00004.bin",
140
+ "transformer.h.7.ln_1.weight": "pytorch_model-00002-of-00004.bin",
141
+ "transformer.h.7.ln_2.bias": "pytorch_model-00002-of-00004.bin",
142
+ "transformer.h.7.ln_2.weight": "pytorch_model-00002-of-00004.bin",
143
+ "transformer.h.7.mlp.c_fc.bias": "pytorch_model-00002-of-00004.bin",
144
+ "transformer.h.7.mlp.c_fc.weight": "pytorch_model-00002-of-00004.bin",
145
+ "transformer.h.7.mlp.c_proj.bias": "pytorch_model-00002-of-00004.bin",
146
+ "transformer.h.7.mlp.c_proj.weight": "pytorch_model-00002-of-00004.bin",
147
+ "transformer.h.8.attn.bias": "pytorch_model-00002-of-00004.bin",
148
+ "transformer.h.8.attn.c_attn.bias": "pytorch_model-00002-of-00004.bin",
149
+ "transformer.h.8.attn.c_attn.weight": "pytorch_model-00002-of-00004.bin",
150
+ "transformer.h.8.attn.c_proj.bias": "pytorch_model-00002-of-00004.bin",
151
+ "transformer.h.8.attn.c_proj.weight": "pytorch_model-00002-of-00004.bin",
152
+ "transformer.h.8.attn.masked_bias": "pytorch_model-00002-of-00004.bin",
153
+ "transformer.h.8.ln_1.bias": "pytorch_model-00002-of-00004.bin",
154
+ "transformer.h.8.ln_1.weight": "pytorch_model-00002-of-00004.bin",
155
+ "transformer.h.8.ln_2.bias": "pytorch_model-00002-of-00004.bin",
156
+ "transformer.h.8.ln_2.weight": "pytorch_model-00002-of-00004.bin",
157
+ "transformer.h.8.mlp.c_fc.bias": "pytorch_model-00003-of-00004.bin",
158
+ "transformer.h.8.mlp.c_fc.weight": "pytorch_model-00003-of-00004.bin",
159
+ "transformer.h.8.mlp.c_proj.bias": "pytorch_model-00003-of-00004.bin",
160
+ "transformer.h.8.mlp.c_proj.weight": "pytorch_model-00003-of-00004.bin",
161
+ "transformer.h.9.attn.bias": "pytorch_model-00003-of-00004.bin",
162
+ "transformer.h.9.attn.c_attn.bias": "pytorch_model-00003-of-00004.bin",
163
+ "transformer.h.9.attn.c_attn.weight": "pytorch_model-00003-of-00004.bin",
164
+ "transformer.h.9.attn.c_proj.bias": "pytorch_model-00003-of-00004.bin",
165
+ "transformer.h.9.attn.c_proj.weight": "pytorch_model-00003-of-00004.bin",
166
+ "transformer.h.9.attn.masked_bias": "pytorch_model-00003-of-00004.bin",
167
+ "transformer.h.9.ln_1.bias": "pytorch_model-00003-of-00004.bin",
168
+ "transformer.h.9.ln_1.weight": "pytorch_model-00003-of-00004.bin",
169
+ "transformer.h.9.ln_2.bias": "pytorch_model-00003-of-00004.bin",
170
+ "transformer.h.9.ln_2.weight": "pytorch_model-00003-of-00004.bin",
171
+ "transformer.h.9.mlp.c_fc.bias": "pytorch_model-00003-of-00004.bin",
172
+ "transformer.h.9.mlp.c_fc.weight": "pytorch_model-00003-of-00004.bin",
173
+ "transformer.h.9.mlp.c_proj.bias": "pytorch_model-00003-of-00004.bin",
174
+ "transformer.h.9.mlp.c_proj.weight": "pytorch_model-00003-of-00004.bin",
175
+ "transformer.ln_f.bias": "pytorch_model-00003-of-00004.bin",
176
+ "transformer.ln_f.weight": "pytorch_model-00003-of-00004.bin",
177
+ "transformer.wpe.weight": "pytorch_model-00001-of-00004.bin",
178
+ "transformer.wte.weight": "pytorch_model-00001-of-00004.bin"
179
+ }
180
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "unk_token": "<|endoftext|>"
5
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<|endoftext|>",
4
+ "eos_token": "<|endoftext|>",
5
+ "model_max_length": 1024,
6
+ "special_tokens_map_file": null,
7
+ "tokenizer_class": "GPT2Tokenizer",
8
+ "unk_token": "<|endoftext|>"
9
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff