Hugging Face's logo

holi-lab
/
diffuGem

Safetensors
Model card Files
xet
 Community
youuor7r commited on
Commit
9349847
·
1 Parent(s): d8ed4cc

modified: retraining

Browse files
Files changed (39) hide show
  1. gpt2-medium-ddm/trainer_log.jsonl +2 -2
  2. gpt2-xl-ddm/trainer_log.jsonl +2 -2
  3. gpt2-xl-pt/checkpoint-120000/config.json +0 -39
  4. gpt2-xl-pt/checkpoint-120000/generation_config.json +0 -6
  5. gpt2-xl-pt/checkpoint-120000/merges.txt +0 -0
  6. gpt2-xl-pt/checkpoint-120000/optimizer.pt +0 -3
  7. gpt2-xl-pt/checkpoint-120000/pytorch_model-00001-of-00002.bin +0 -3
  8. gpt2-xl-pt/checkpoint-120000/pytorch_model-00002-of-00002.bin +0 -3
  9. gpt2-xl-pt/checkpoint-120000/pytorch_model.bin.index.json +0 -588
  10. gpt2-xl-pt/checkpoint-120000/rng_state_0.pth +0 -3
  11. gpt2-xl-pt/checkpoint-120000/rng_state_1.pth +0 -3
  12. gpt2-xl-pt/checkpoint-120000/rng_state_2.pth +0 -3
  13. gpt2-xl-pt/checkpoint-120000/rng_state_3.pth +0 -3
  14. gpt2-xl-pt/checkpoint-120000/scheduler.pt +0 -3
  15. gpt2-xl-pt/checkpoint-120000/special_tokens_map.json +0 -8
  16. gpt2-xl-pt/checkpoint-120000/tokenizer.json +0 -3
  17. gpt2-xl-pt/checkpoint-120000/tokenizer_config.json +0 -26
  18. gpt2-xl-pt/checkpoint-120000/trainer_state.json +0 -0
  19. gpt2-xl-pt/checkpoint-120000/training_args.bin +0 -3
  20. gpt2-xl-pt/checkpoint-120000/vocab.json +0 -0
  21. gpt2-xl-pt/checkpoint-240000/config.json +0 -39
  22. gpt2-xl-pt/checkpoint-240000/generation_config.json +0 -6
  23. gpt2-xl-pt/checkpoint-240000/merges.txt +0 -0
  24. gpt2-xl-pt/checkpoint-240000/optimizer.pt +0 -3
  25. gpt2-xl-pt/checkpoint-240000/pytorch_model-00001-of-00002.bin +0 -3
  26. gpt2-xl-pt/checkpoint-240000/pytorch_model-00002-of-00002.bin +0 -3
  27. gpt2-xl-pt/checkpoint-240000/pytorch_model.bin.index.json +0 -588
  28. gpt2-xl-pt/checkpoint-240000/rng_state_0.pth +0 -3
  29. gpt2-xl-pt/checkpoint-240000/rng_state_1.pth +0 -3
  30. gpt2-xl-pt/checkpoint-240000/rng_state_2.pth +0 -3
  31. gpt2-xl-pt/checkpoint-240000/rng_state_3.pth +0 -3
  32. gpt2-xl-pt/checkpoint-240000/scheduler.pt +0 -3
  33. gpt2-xl-pt/checkpoint-240000/special_tokens_map.json +0 -8
  34. gpt2-xl-pt/checkpoint-240000/tokenizer.json +0 -3
  35. gpt2-xl-pt/checkpoint-240000/tokenizer_config.json +0 -26
  36. gpt2-xl-pt/checkpoint-240000/trainer_state.json +0 -0
  37. gpt2-xl-pt/checkpoint-240000/training_args.bin +0 -3
  38. gpt2-xl-pt/checkpoint-240000/vocab.json +0 -0
  39. gpt2-xl-pt/trainer_log.jsonl +2 -2
gpt2-medium-ddm/trainer_log.jsonl CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:efea14477b2005a0f791cc2fece9b40efb7fa6a45b310027d6178d084a768cde
3
- size 129635
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c63c748fdb593caa164dee96453c9bffca6a6bb1a281e298594751827354dacc
3
+ size 438322
gpt2-xl-ddm/trainer_log.jsonl CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:96ccbf8878df3fce83b3cb8b761579f5d2fe06b3ce7a8b442d69a12c3fea9fd0
3
- size 30828
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ca331b9cf6277a454830aa956ddfb79de345c36c64fe055273725da3103a5bc
3
+ size 56520
gpt2-xl-pt/checkpoint-120000/config.json DELETED
@@ -1,39 +0,0 @@
1
- {
2
- "activation_function": "gelu_new",
3
- "architectures": [
4
- "GPT2LMHeadModel"
5
- ],
6
- "attn_pdrop": 0.1,
7
- "bos_token_id": 50256,
8
- "embd_pdrop": 0.1,
9
- "eos_token_id": 50256,
10
- "initializer_range": 0.02,
11
- "layer_norm_epsilon": 1e-05,
12
- "model_type": "gpt2",
13
- "n_ctx": 1024,
14
- "n_embd": 1600,
15
- "n_head": 25,
16
- "n_inner": null,
17
- "n_layer": 48,
18
- "n_positions": 1024,
19
- "output_past": true,
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": "4.50.3",
37
- "use_cache": false,
38
- "vocab_size": 50257
39
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
gpt2-xl-pt/checkpoint-120000/generation_config.json DELETED
@@ -1,6 +0,0 @@
1
- {
2
- "_from_model_config": true,
3
- "bos_token_id": 50256,
4
- "eos_token_id": 50256,
5
- "transformers_version": "4.50.3"
6
- }
 
 
 
 
 
 
 
gpt2-xl-pt/checkpoint-120000/merges.txt DELETED
The diff for this file is too large to render. See raw diff
 
gpt2-xl-pt/checkpoint-120000/optimizer.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:d448137af716c9ec3a7f8829783717bbe29e36fb6d246df151bb8d22535637f0
3
- size 12461385454
 
 
 
 
gpt2-xl-pt/checkpoint-120000/pytorch_model-00001-of-00002.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:cdbc84561a06fedce20da1377e28990584660c85a9c2151f3426d21a3b33d15d
3
- size 4959990818
 
 
 
 
gpt2-xl-pt/checkpoint-120000/pytorch_model-00002-of-00002.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:5c18733fa48a7bae1432e1693c3f49ded3f6a3bd48121bddfbb15a553e51f5ad
3
- size 1270653818
 
 
 
 
gpt2-xl-pt/checkpoint-120000/pytorch_model.bin.index.json DELETED
@@ -1,588 +0,0 @@
1
- {
2
- "metadata": {
3
- "total_size": 6230444800
4
- },
5
- "weight_map": {
6
- "lm_head.weight": "pytorch_model-00001-of-00002.bin",
7
- "transformer.h.0.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
8
- "transformer.h.0.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
9
- "transformer.h.0.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
10
- "transformer.h.0.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
11
- "transformer.h.0.ln_1.bias": "pytorch_model-00001-of-00002.bin",
12
- "transformer.h.0.ln_1.weight": "pytorch_model-00001-of-00002.bin",
13
- "transformer.h.0.ln_2.bias": "pytorch_model-00001-of-00002.bin",
14
- "transformer.h.0.ln_2.weight": "pytorch_model-00001-of-00002.bin",
15
- "transformer.h.0.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
16
- "transformer.h.0.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
17
- "transformer.h.0.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
18
- "transformer.h.0.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
19
- "transformer.h.1.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
20
- "transformer.h.1.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
21
- "transformer.h.1.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
22
- "transformer.h.1.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
23
- "transformer.h.1.ln_1.bias": "pytorch_model-00001-of-00002.bin",
24
- "transformer.h.1.ln_1.weight": "pytorch_model-00001-of-00002.bin",
25
- "transformer.h.1.ln_2.bias": "pytorch_model-00001-of-00002.bin",
26
- "transformer.h.1.ln_2.weight": "pytorch_model-00001-of-00002.bin",
27
- "transformer.h.1.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
28
- "transformer.h.1.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
29
- "transformer.h.1.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
30
- "transformer.h.1.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
31
- "transformer.h.10.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
32
- "transformer.h.10.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
33
- "transformer.h.10.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
34
- "transformer.h.10.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
35
- "transformer.h.10.ln_1.bias": "pytorch_model-00001-of-00002.bin",
36
- "transformer.h.10.ln_1.weight": "pytorch_model-00001-of-00002.bin",
37
- "transformer.h.10.ln_2.bias": "pytorch_model-00001-of-00002.bin",
38
- "transformer.h.10.ln_2.weight": "pytorch_model-00001-of-00002.bin",
39
- "transformer.h.10.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
40
- "transformer.h.10.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
41
- "transformer.h.10.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
42
- "transformer.h.10.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
43
- "transformer.h.11.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
44
- "transformer.h.11.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
45
- "transformer.h.11.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
46
- "transformer.h.11.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
47
- "transformer.h.11.ln_1.bias": "pytorch_model-00001-of-00002.bin",
48
- "transformer.h.11.ln_1.weight": "pytorch_model-00001-of-00002.bin",
49
- "transformer.h.11.ln_2.bias": "pytorch_model-00001-of-00002.bin",
50
- "transformer.h.11.ln_2.weight": "pytorch_model-00001-of-00002.bin",
51
- "transformer.h.11.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
52
- "transformer.h.11.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
53
- "transformer.h.11.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
54
- "transformer.h.11.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
55
- "transformer.h.12.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
56
- "transformer.h.12.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
57
- "transformer.h.12.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
58
- "transformer.h.12.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
59
- "transformer.h.12.ln_1.bias": "pytorch_model-00001-of-00002.bin",
60
- "transformer.h.12.ln_1.weight": "pytorch_model-00001-of-00002.bin",
61
- "transformer.h.12.ln_2.bias": "pytorch_model-00001-of-00002.bin",
62
- "transformer.h.12.ln_2.weight": "pytorch_model-00001-of-00002.bin",
63
- "transformer.h.12.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
64
- "transformer.h.12.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
65
- "transformer.h.12.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
66
- "transformer.h.12.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
67
- "transformer.h.13.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
68
- "transformer.h.13.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
69
- "transformer.h.13.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
70
- "transformer.h.13.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
71
- "transformer.h.13.ln_1.bias": "pytorch_model-00001-of-00002.bin",
72
- "transformer.h.13.ln_1.weight": "pytorch_model-00001-of-00002.bin",
73
- "transformer.h.13.ln_2.bias": "pytorch_model-00001-of-00002.bin",
74
- "transformer.h.13.ln_2.weight": "pytorch_model-00001-of-00002.bin",
75
- "transformer.h.13.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
76
- "transformer.h.13.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
77
- "transformer.h.13.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
78
- "transformer.h.13.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
79
- "transformer.h.14.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
80
- "transformer.h.14.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
81
- "transformer.h.14.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
82
- "transformer.h.14.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
83
- "transformer.h.14.ln_1.bias": "pytorch_model-00001-of-00002.bin",
84
- "transformer.h.14.ln_1.weight": "pytorch_model-00001-of-00002.bin",
85
- "transformer.h.14.ln_2.bias": "pytorch_model-00001-of-00002.bin",
86
- "transformer.h.14.ln_2.weight": "pytorch_model-00001-of-00002.bin",
87
- "transformer.h.14.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
88
- "transformer.h.14.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
89
- "transformer.h.14.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
90
- "transformer.h.14.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
91
- "transformer.h.15.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
92
- "transformer.h.15.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
93
- "transformer.h.15.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
94
- "transformer.h.15.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
95
- "transformer.h.15.ln_1.bias": "pytorch_model-00001-of-00002.bin",
96
- "transformer.h.15.ln_1.weight": "pytorch_model-00001-of-00002.bin",
97
- "transformer.h.15.ln_2.bias": "pytorch_model-00001-of-00002.bin",
98
- "transformer.h.15.ln_2.weight": "pytorch_model-00001-of-00002.bin",
99
- "transformer.h.15.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
100
- "transformer.h.15.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
101
- "transformer.h.15.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
102
- "transformer.h.15.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
103
- "transformer.h.16.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
104
- "transformer.h.16.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
105
- "transformer.h.16.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
106
- "transformer.h.16.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
107
- "transformer.h.16.ln_1.bias": "pytorch_model-00001-of-00002.bin",
108
- "transformer.h.16.ln_1.weight": "pytorch_model-00001-of-00002.bin",
109
- "transformer.h.16.ln_2.bias": "pytorch_model-00001-of-00002.bin",
110
- "transformer.h.16.ln_2.weight": "pytorch_model-00001-of-00002.bin",
111
- "transformer.h.16.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
112
- "transformer.h.16.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
113
- "transformer.h.16.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
114
- "transformer.h.16.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
115
- "transformer.h.17.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
116
- "transformer.h.17.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
117
- "transformer.h.17.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
118
- "transformer.h.17.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
119
- "transformer.h.17.ln_1.bias": "pytorch_model-00001-of-00002.bin",
120
- "transformer.h.17.ln_1.weight": "pytorch_model-00001-of-00002.bin",
121
- "transformer.h.17.ln_2.bias": "pytorch_model-00001-of-00002.bin",
122
- "transformer.h.17.ln_2.weight": "pytorch_model-00001-of-00002.bin",
123
- "transformer.h.17.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
124
- "transformer.h.17.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
125
- "transformer.h.17.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
126
- "transformer.h.17.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
127
- "transformer.h.18.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
128
- "transformer.h.18.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
129
- "transformer.h.18.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
130
- "transformer.h.18.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
131
- "transformer.h.18.ln_1.bias": "pytorch_model-00001-of-00002.bin",
132
- "transformer.h.18.ln_1.weight": "pytorch_model-00001-of-00002.bin",
133
- "transformer.h.18.ln_2.bias": "pytorch_model-00001-of-00002.bin",
134
- "transformer.h.18.ln_2.weight": "pytorch_model-00001-of-00002.bin",
135
- "transformer.h.18.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
136
- "transformer.h.18.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
137
- "transformer.h.18.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
138
- "transformer.h.18.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
139
- "transformer.h.19.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
140
- "transformer.h.19.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
141
- "transformer.h.19.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
142
- "transformer.h.19.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
143
- "transformer.h.19.ln_1.bias": "pytorch_model-00001-of-00002.bin",
144
- "transformer.h.19.ln_1.weight": "pytorch_model-00001-of-00002.bin",
145
- "transformer.h.19.ln_2.bias": "pytorch_model-00001-of-00002.bin",
146
- "transformer.h.19.ln_2.weight": "pytorch_model-00001-of-00002.bin",
147
- "transformer.h.19.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
148
- "transformer.h.19.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
149
- "transformer.h.19.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
150
- "transformer.h.19.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
151
- "transformer.h.2.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
152
- "transformer.h.2.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
153
- "transformer.h.2.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
154
- "transformer.h.2.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
155
- "transformer.h.2.ln_1.bias": "pytorch_model-00001-of-00002.bin",
156
- "transformer.h.2.ln_1.weight": "pytorch_model-00001-of-00002.bin",
157
- "transformer.h.2.ln_2.bias": "pytorch_model-00001-of-00002.bin",
158
- "transformer.h.2.ln_2.weight": "pytorch_model-00001-of-00002.bin",
159
- "transformer.h.2.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
160
- "transformer.h.2.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
161
- "transformer.h.2.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
162
- "transformer.h.2.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
163
- "transformer.h.20.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
164
- "transformer.h.20.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
165
- "transformer.h.20.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
166
- "transformer.h.20.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
167
- "transformer.h.20.ln_1.bias": "pytorch_model-00001-of-00002.bin",
168
- "transformer.h.20.ln_1.weight": "pytorch_model-00001-of-00002.bin",
169
- "transformer.h.20.ln_2.bias": "pytorch_model-00001-of-00002.bin",
170
- "transformer.h.20.ln_2.weight": "pytorch_model-00001-of-00002.bin",
171
- "transformer.h.20.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
172
- "transformer.h.20.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
173
- "transformer.h.20.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
174
- "transformer.h.20.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
175
- "transformer.h.21.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
176
- "transformer.h.21.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
177
- "transformer.h.21.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
178
- "transformer.h.21.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
179
- "transformer.h.21.ln_1.bias": "pytorch_model-00001-of-00002.bin",
180
- "transformer.h.21.ln_1.weight": "pytorch_model-00001-of-00002.bin",
181
- "transformer.h.21.ln_2.bias": "pytorch_model-00001-of-00002.bin",
182
- "transformer.h.21.ln_2.weight": "pytorch_model-00001-of-00002.bin",
183
- "transformer.h.21.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
184
- "transformer.h.21.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
185
- "transformer.h.21.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
186
- "transformer.h.21.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
187
- "transformer.h.22.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
188
- "transformer.h.22.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
189
- "transformer.h.22.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
190
- "transformer.h.22.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
191
- "transformer.h.22.ln_1.bias": "pytorch_model-00001-of-00002.bin",
192
- "transformer.h.22.ln_1.weight": "pytorch_model-00001-of-00002.bin",
193
- "transformer.h.22.ln_2.bias": "pytorch_model-00001-of-00002.bin",
194
- "transformer.h.22.ln_2.weight": "pytorch_model-00001-of-00002.bin",
195
- "transformer.h.22.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
196
- "transformer.h.22.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
197
- "transformer.h.22.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
198
- "transformer.h.22.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
199
- "transformer.h.23.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
200
- "transformer.h.23.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
201
- "transformer.h.23.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
202
- "transformer.h.23.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
203
- "transformer.h.23.ln_1.bias": "pytorch_model-00001-of-00002.bin",
204
- "transformer.h.23.ln_1.weight": "pytorch_model-00001-of-00002.bin",
205
- "transformer.h.23.ln_2.bias": "pytorch_model-00001-of-00002.bin",
206
- "transformer.h.23.ln_2.weight": "pytorch_model-00001-of-00002.bin",
207
- "transformer.h.23.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
208
- "transformer.h.23.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
209
- "transformer.h.23.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
210
- "transformer.h.23.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
211
- "transformer.h.24.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
212
- "transformer.h.24.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
213
- "transformer.h.24.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
214
- "transformer.h.24.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
215
- "transformer.h.24.ln_1.bias": "pytorch_model-00001-of-00002.bin",
216
- "transformer.h.24.ln_1.weight": "pytorch_model-00001-of-00002.bin",
217
- "transformer.h.24.ln_2.bias": "pytorch_model-00001-of-00002.bin",
218
- "transformer.h.24.ln_2.weight": "pytorch_model-00001-of-00002.bin",
219
- "transformer.h.24.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
220
- "transformer.h.24.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
221
- "transformer.h.24.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
222
- "transformer.h.24.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
223
- "transformer.h.25.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
224
- "transformer.h.25.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
225
- "transformer.h.25.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
226
- "transformer.h.25.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
227
- "transformer.h.25.ln_1.bias": "pytorch_model-00001-of-00002.bin",
228
- "transformer.h.25.ln_1.weight": "pytorch_model-00001-of-00002.bin",
229
- "transformer.h.25.ln_2.bias": "pytorch_model-00001-of-00002.bin",
230
- "transformer.h.25.ln_2.weight": "pytorch_model-00001-of-00002.bin",
231
- "transformer.h.25.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
232
- "transformer.h.25.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
233
- "transformer.h.25.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
234
- "transformer.h.25.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
235
- "transformer.h.26.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
236
- "transformer.h.26.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
237
- "transformer.h.26.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
238
- "transformer.h.26.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
239
- "transformer.h.26.ln_1.bias": "pytorch_model-00001-of-00002.bin",
240
- "transformer.h.26.ln_1.weight": "pytorch_model-00001-of-00002.bin",
241
- "transformer.h.26.ln_2.bias": "pytorch_model-00001-of-00002.bin",
242
- "transformer.h.26.ln_2.weight": "pytorch_model-00001-of-00002.bin",
243
- "transformer.h.26.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
244
- "transformer.h.26.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
245
- "transformer.h.26.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
246
- "transformer.h.26.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
247
- "transformer.h.27.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
248
- "transformer.h.27.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
249
- "transformer.h.27.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
250
- "transformer.h.27.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
251
- "transformer.h.27.ln_1.bias": "pytorch_model-00001-of-00002.bin",
252
- "transformer.h.27.ln_1.weight": "pytorch_model-00001-of-00002.bin",
253
- "transformer.h.27.ln_2.bias": "pytorch_model-00001-of-00002.bin",
254
- "transformer.h.27.ln_2.weight": "pytorch_model-00001-of-00002.bin",
255
- "transformer.h.27.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
256
- "transformer.h.27.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
257
- "transformer.h.27.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
258
- "transformer.h.27.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
259
- "transformer.h.28.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
260
- "transformer.h.28.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
261
- "transformer.h.28.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
262
- "transformer.h.28.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
263
- "transformer.h.28.ln_1.bias": "pytorch_model-00001-of-00002.bin",
264
- "transformer.h.28.ln_1.weight": "pytorch_model-00001-of-00002.bin",
265
- "transformer.h.28.ln_2.bias": "pytorch_model-00001-of-00002.bin",
266
- "transformer.h.28.ln_2.weight": "pytorch_model-00001-of-00002.bin",
267
- "transformer.h.28.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
268
- "transformer.h.28.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
269
- "transformer.h.28.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
270
- "transformer.h.28.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
271
- "transformer.h.29.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
272
- "transformer.h.29.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
273
- "transformer.h.29.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
274
- "transformer.h.29.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
275
- "transformer.h.29.ln_1.bias": "pytorch_model-00001-of-00002.bin",
276
- "transformer.h.29.ln_1.weight": "pytorch_model-00001-of-00002.bin",
277
- "transformer.h.29.ln_2.bias": "pytorch_model-00001-of-00002.bin",
278
- "transformer.h.29.ln_2.weight": "pytorch_model-00001-of-00002.bin",
279
- "transformer.h.29.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
280
- "transformer.h.29.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
281
- "transformer.h.29.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
282
- "transformer.h.29.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
283
- "transformer.h.3.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
284
- "transformer.h.3.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
285
- "transformer.h.3.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
286
- "transformer.h.3.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
287
- "transformer.h.3.ln_1.bias": "pytorch_model-00001-of-00002.bin",
288
- "transformer.h.3.ln_1.weight": "pytorch_model-00001-of-00002.bin",
289
- "transformer.h.3.ln_2.bias": "pytorch_model-00001-of-00002.bin",
290
- "transformer.h.3.ln_2.weight": "pytorch_model-00001-of-00002.bin",
291
- "transformer.h.3.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
292
- "transformer.h.3.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
293
- "transformer.h.3.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
294
- "transformer.h.3.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
295
- "transformer.h.30.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
296
- "transformer.h.30.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
297
- "transformer.h.30.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
298
- "transformer.h.30.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
299
- "transformer.h.30.ln_1.bias": "pytorch_model-00001-of-00002.bin",
300
- "transformer.h.30.ln_1.weight": "pytorch_model-00001-of-00002.bin",
301
- "transformer.h.30.ln_2.bias": "pytorch_model-00001-of-00002.bin",
302
- "transformer.h.30.ln_2.weight": "pytorch_model-00001-of-00002.bin",
303
- "transformer.h.30.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
304
- "transformer.h.30.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
305
- "transformer.h.30.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
306
- "transformer.h.30.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
307
- "transformer.h.31.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
308
- "transformer.h.31.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
309
- "transformer.h.31.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
310
- "transformer.h.31.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
311
- "transformer.h.31.ln_1.bias": "pytorch_model-00001-of-00002.bin",
312
- "transformer.h.31.ln_1.weight": "pytorch_model-00001-of-00002.bin",
313
- "transformer.h.31.ln_2.bias": "pytorch_model-00001-of-00002.bin",
314
- "transformer.h.31.ln_2.weight": "pytorch_model-00001-of-00002.bin",
315
- "transformer.h.31.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
316
- "transformer.h.31.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
317
- "transformer.h.31.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
318
- "transformer.h.31.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
319
- "transformer.h.32.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
320
- "transformer.h.32.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
321
- "transformer.h.32.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
322
- "transformer.h.32.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
323
- "transformer.h.32.ln_1.bias": "pytorch_model-00001-of-00002.bin",
324
- "transformer.h.32.ln_1.weight": "pytorch_model-00001-of-00002.bin",
325
- "transformer.h.32.ln_2.bias": "pytorch_model-00001-of-00002.bin",
326
- "transformer.h.32.ln_2.weight": "pytorch_model-00001-of-00002.bin",
327
- "transformer.h.32.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
328
- "transformer.h.32.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
329
- "transformer.h.32.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
330
- "transformer.h.32.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
331
- "transformer.h.33.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
332
- "transformer.h.33.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
333
- "transformer.h.33.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
334
- "transformer.h.33.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
335
- "transformer.h.33.ln_1.bias": "pytorch_model-00001-of-00002.bin",
336
- "transformer.h.33.ln_1.weight": "pytorch_model-00001-of-00002.bin",
337
- "transformer.h.33.ln_2.bias": "pytorch_model-00001-of-00002.bin",
338
- "transformer.h.33.ln_2.weight": "pytorch_model-00001-of-00002.bin",
339
- "transformer.h.33.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
340
- "transformer.h.33.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
341
- "transformer.h.33.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
342
- "transformer.h.33.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
343
- "transformer.h.34.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
344
- "transformer.h.34.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
345
- "transformer.h.34.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
346
- "transformer.h.34.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
347
- "transformer.h.34.ln_1.bias": "pytorch_model-00001-of-00002.bin",
348
- "transformer.h.34.ln_1.weight": "pytorch_model-00001-of-00002.bin",
349
- "transformer.h.34.ln_2.bias": "pytorch_model-00001-of-00002.bin",
350
- "transformer.h.34.ln_2.weight": "pytorch_model-00001-of-00002.bin",
351
- "transformer.h.34.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
352
- "transformer.h.34.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
353
- "transformer.h.34.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
354
- "transformer.h.34.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
355
- "transformer.h.35.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
356
- "transformer.h.35.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
357
- "transformer.h.35.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
358
- "transformer.h.35.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
359
- "transformer.h.35.ln_1.bias": "pytorch_model-00001-of-00002.bin",
360
- "transformer.h.35.ln_1.weight": "pytorch_model-00001-of-00002.bin",
361
- "transformer.h.35.ln_2.bias": "pytorch_model-00001-of-00002.bin",
362
- "transformer.h.35.ln_2.weight": "pytorch_model-00001-of-00002.bin",
363
- "transformer.h.35.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
364
- "transformer.h.35.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
365
- "transformer.h.35.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
366
- "transformer.h.35.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
367
- "transformer.h.36.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
368
- "transformer.h.36.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
369
- "transformer.h.36.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
370
- "transformer.h.36.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
371
- "transformer.h.36.ln_1.bias": "pytorch_model-00001-of-00002.bin",
372
- "transformer.h.36.ln_1.weight": "pytorch_model-00001-of-00002.bin",
373
- "transformer.h.36.ln_2.bias": "pytorch_model-00001-of-00002.bin",
374
- "transformer.h.36.ln_2.weight": "pytorch_model-00001-of-00002.bin",
375
- "transformer.h.36.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
376
- "transformer.h.36.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
377
- "transformer.h.36.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
378
- "transformer.h.36.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
379
- "transformer.h.37.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
380
- "transformer.h.37.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
381
- "transformer.h.37.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
382
- "transformer.h.37.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
383
- "transformer.h.37.ln_1.bias": "pytorch_model-00001-of-00002.bin",
384
- "transformer.h.37.ln_1.weight": "pytorch_model-00001-of-00002.bin",
385
- "transformer.h.37.ln_2.bias": "pytorch_model-00001-of-00002.bin",
386
- "transformer.h.37.ln_2.weight": "pytorch_model-00001-of-00002.bin",
387
- "transformer.h.37.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
388
- "transformer.h.37.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
389
- "transformer.h.37.mlp.c_proj.bias": "pytorch_model-00002-of-00002.bin",
390
- "transformer.h.37.mlp.c_proj.weight": "pytorch_model-00002-of-00002.bin",
391
- "transformer.h.38.attn.c_attn.bias": "pytorch_model-00002-of-00002.bin",
392
- "transformer.h.38.attn.c_attn.weight": "pytorch_model-00002-of-00002.bin",
393
- "transformer.h.38.attn.c_proj.bias": "pytorch_model-00002-of-00002.bin",
394
- "transformer.h.38.attn.c_proj.weight": "pytorch_model-00002-of-00002.bin",
395
- "transformer.h.38.ln_1.bias": "pytorch_model-00002-of-00002.bin",
396
- "transformer.h.38.ln_1.weight": "pytorch_model-00002-of-00002.bin",
397
- "transformer.h.38.ln_2.bias": "pytorch_model-00002-of-00002.bin",
398
- "transformer.h.38.ln_2.weight": "pytorch_model-00002-of-00002.bin",
399
- "transformer.h.38.mlp.c_fc.bias": "pytorch_model-00002-of-00002.bin",
400
- "transformer.h.38.mlp.c_fc.weight": "pytorch_model-00002-of-00002.bin",
401
- "transformer.h.38.mlp.c_proj.bias": "pytorch_model-00002-of-00002.bin",
402
- "transformer.h.38.mlp.c_proj.weight": "pytorch_model-00002-of-00002.bin",
403
- "transformer.h.39.attn.c_attn.bias": "pytorch_model-00002-of-00002.bin",
404
- "transformer.h.39.attn.c_attn.weight": "pytorch_model-00002-of-00002.bin",
405
- "transformer.h.39.attn.c_proj.bias": "pytorch_model-00002-of-00002.bin",
406
- "transformer.h.39.attn.c_proj.weight": "pytorch_model-00002-of-00002.bin",
407
- "transformer.h.39.ln_1.bias": "pytorch_model-00002-of-00002.bin",
408
- "transformer.h.39.ln_1.weight": "pytorch_model-00002-of-00002.bin",
409
- "transformer.h.39.ln_2.bias": "pytorch_model-00002-of-00002.bin",
410
- "transformer.h.39.ln_2.weight": "pytorch_model-00002-of-00002.bin",
411
- "transformer.h.39.mlp.c_fc.bias": "pytorch_model-00002-of-00002.bin",
412
- "transformer.h.39.mlp.c_fc.weight": "pytorch_model-00002-of-00002.bin",
413
- "transformer.h.39.mlp.c_proj.bias": "pytorch_model-00002-of-00002.bin",
414
- "transformer.h.39.mlp.c_proj.weight": "pytorch_model-00002-of-00002.bin",
415
- "transformer.h.4.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
416
- "transformer.h.4.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
417
- "transformer.h.4.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
418
- "transformer.h.4.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
419
- "transformer.h.4.ln_1.bias": "pytorch_model-00001-of-00002.bin",
420
- "transformer.h.4.ln_1.weight": "pytorch_model-00001-of-00002.bin",
421
- "transformer.h.4.ln_2.bias": "pytorch_model-00001-of-00002.bin",
422
- "transformer.h.4.ln_2.weight": "pytorch_model-00001-of-00002.bin",
423
- "transformer.h.4.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
424
- "transformer.h.4.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
425
- "transformer.h.4.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
426
- "transformer.h.4.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
427
- "transformer.h.40.attn.c_attn.bias": "pytorch_model-00002-of-00002.bin",
428
- "transformer.h.40.attn.c_attn.weight": "pytorch_model-00002-of-00002.bin",
429
- "transformer.h.40.attn.c_proj.bias": "pytorch_model-00002-of-00002.bin",
430
- "transformer.h.40.attn.c_proj.weight": "pytorch_model-00002-of-00002.bin",
431
- "transformer.h.40.ln_1.bias": "pytorch_model-00002-of-00002.bin",
432
- "transformer.h.40.ln_1.weight": "pytorch_model-00002-of-00002.bin",
433
- "transformer.h.40.ln_2.bias": "pytorch_model-00002-of-00002.bin",
434
- "transformer.h.40.ln_2.weight": "pytorch_model-00002-of-00002.bin",
435
- "transformer.h.40.mlp.c_fc.bias": "pytorch_model-00002-of-00002.bin",
436
- "transformer.h.40.mlp.c_fc.weight": "pytorch_model-00002-of-00002.bin",
437
- "transformer.h.40.mlp.c_proj.bias": "pytorch_model-00002-of-00002.bin",
438
- "transformer.h.40.mlp.c_proj.weight": "pytorch_model-00002-of-00002.bin",
439
- "transformer.h.41.attn.c_attn.bias": "pytorch_model-00002-of-00002.bin",
440
- "transformer.h.41.attn.c_attn.weight": "pytorch_model-00002-of-00002.bin",
441
- "transformer.h.41.attn.c_proj.bias": "pytorch_model-00002-of-00002.bin",
442
- "transformer.h.41.attn.c_proj.weight": "pytorch_model-00002-of-00002.bin",
443
- "transformer.h.41.ln_1.bias": "pytorch_model-00002-of-00002.bin",
444
- "transformer.h.41.ln_1.weight": "pytorch_model-00002-of-00002.bin",
445
- "transformer.h.41.ln_2.bias": "pytorch_model-00002-of-00002.bin",
446
- "transformer.h.41.ln_2.weight": "pytorch_model-00002-of-00002.bin",
447
- "transformer.h.41.mlp.c_fc.bias": "pytorch_model-00002-of-00002.bin",
448
- "transformer.h.41.mlp.c_fc.weight": "pytorch_model-00002-of-00002.bin",
449
- "transformer.h.41.mlp.c_proj.bias": "pytorch_model-00002-of-00002.bin",
450
- "transformer.h.41.mlp.c_proj.weight": "pytorch_model-00002-of-00002.bin",
451
- "transformer.h.42.attn.c_attn.bias": "pytorch_model-00002-of-00002.bin",
452
- "transformer.h.42.attn.c_attn.weight": "pytorch_model-00002-of-00002.bin",
453
- "transformer.h.42.attn.c_proj.bias": "pytorch_model-00002-of-00002.bin",
454
- "transformer.h.42.attn.c_proj.weight": "pytorch_model-00002-of-00002.bin",
455
- "transformer.h.42.ln_1.bias": "pytorch_model-00002-of-00002.bin",
456
- "transformer.h.42.ln_1.weight": "pytorch_model-00002-of-00002.bin",
457
- "transformer.h.42.ln_2.bias": "pytorch_model-00002-of-00002.bin",
458
- "transformer.h.42.ln_2.weight": "pytorch_model-00002-of-00002.bin",
459
- "transformer.h.42.mlp.c_fc.bias": "pytorch_model-00002-of-00002.bin",
460
- "transformer.h.42.mlp.c_fc.weight": "pytorch_model-00002-of-00002.bin",
461
- "transformer.h.42.mlp.c_proj.bias": "pytorch_model-00002-of-00002.bin",
462
- "transformer.h.42.mlp.c_proj.weight": "pytorch_model-00002-of-00002.bin",
463
- "transformer.h.43.attn.c_attn.bias": "pytorch_model-00002-of-00002.bin",
464
- "transformer.h.43.attn.c_attn.weight": "pytorch_model-00002-of-00002.bin",
465
- "transformer.h.43.attn.c_proj.bias": "pytorch_model-00002-of-00002.bin",
466
- "transformer.h.43.attn.c_proj.weight": "pytorch_model-00002-of-00002.bin",
467
- "transformer.h.43.ln_1.bias": "pytorch_model-00002-of-00002.bin",
468
- "transformer.h.43.ln_1.weight": "pytorch_model-00002-of-00002.bin",
469
- "transformer.h.43.ln_2.bias": "pytorch_model-00002-of-00002.bin",
470
- "transformer.h.43.ln_2.weight": "pytorch_model-00002-of-00002.bin",
471
- "transformer.h.43.mlp.c_fc.bias": "pytorch_model-00002-of-00002.bin",
472
- "transformer.h.43.mlp.c_fc.weight": "pytorch_model-00002-of-00002.bin",
473
- "transformer.h.43.mlp.c_proj.bias": "pytorch_model-00002-of-00002.bin",
474
- "transformer.h.43.mlp.c_proj.weight": "pytorch_model-00002-of-00002.bin",
475
- "transformer.h.44.attn.c_attn.bias": "pytorch_model-00002-of-00002.bin",
476
- "transformer.h.44.attn.c_attn.weight": "pytorch_model-00002-of-00002.bin",
477
- "transformer.h.44.attn.c_proj.bias": "pytorch_model-00002-of-00002.bin",
478
- "transformer.h.44.attn.c_proj.weight": "pytorch_model-00002-of-00002.bin",
479
- "transformer.h.44.ln_1.bias": "pytorch_model-00002-of-00002.bin",
480
- "transformer.h.44.ln_1.weight": "pytorch_model-00002-of-00002.bin",
481
- "transformer.h.44.ln_2.bias": "pytorch_model-00002-of-00002.bin",
482
- "transformer.h.44.ln_2.weight": "pytorch_model-00002-of-00002.bin",
483
- "transformer.h.44.mlp.c_fc.bias": "pytorch_model-00002-of-00002.bin",
484
- "transformer.h.44.mlp.c_fc.weight": "pytorch_model-00002-of-00002.bin",
485
- "transformer.h.44.mlp.c_proj.bias": "pytorch_model-00002-of-00002.bin",
486
- "transformer.h.44.mlp.c_proj.weight": "pytorch_model-00002-of-00002.bin",
487
- "transformer.h.45.attn.c_attn.bias": "pytorch_model-00002-of-00002.bin",
488
- "transformer.h.45.attn.c_attn.weight": "pytorch_model-00002-of-00002.bin",
489
- "transformer.h.45.attn.c_proj.bias": "pytorch_model-00002-of-00002.bin",
490
- "transformer.h.45.attn.c_proj.weight": "pytorch_model-00002-of-00002.bin",
491
- "transformer.h.45.ln_1.bias": "pytorch_model-00002-of-00002.bin",
492
- "transformer.h.45.ln_1.weight": "pytorch_model-00002-of-00002.bin",
493
- "transformer.h.45.ln_2.bias": "pytorch_model-00002-of-00002.bin",
494
- "transformer.h.45.ln_2.weight": "pytorch_model-00002-of-00002.bin",
495
- "transformer.h.45.mlp.c_fc.bias": "pytorch_model-00002-of-00002.bin",
496
- "transformer.h.45.mlp.c_fc.weight": "pytorch_model-00002-of-00002.bin",
497
- "transformer.h.45.mlp.c_proj.bias": "pytorch_model-00002-of-00002.bin",
498
- "transformer.h.45.mlp.c_proj.weight": "pytorch_model-00002-of-00002.bin",
499
- "transformer.h.46.attn.c_attn.bias": "pytorch_model-00002-of-00002.bin",
500
- "transformer.h.46.attn.c_attn.weight": "pytorch_model-00002-of-00002.bin",
501
- "transformer.h.46.attn.c_proj.bias": "pytorch_model-00002-of-00002.bin",
502
- "transformer.h.46.attn.c_proj.weight": "pytorch_model-00002-of-00002.bin",
503
- "transformer.h.46.ln_1.bias": "pytorch_model-00002-of-00002.bin",
504
- "transformer.h.46.ln_1.weight": "pytorch_model-00002-of-00002.bin",
505
- "transformer.h.46.ln_2.bias": "pytorch_model-00002-of-00002.bin",
506
- "transformer.h.46.ln_2.weight": "pytorch_model-00002-of-00002.bin",
507
- "transformer.h.46.mlp.c_fc.bias": "pytorch_model-00002-of-00002.bin",
508
- "transformer.h.46.mlp.c_fc.weight": "pytorch_model-00002-of-00002.bin",
509
- "transformer.h.46.mlp.c_proj.bias": "pytorch_model-00002-of-00002.bin",
510
- "transformer.h.46.mlp.c_proj.weight": "pytorch_model-00002-of-00002.bin",
511
- "transformer.h.47.attn.c_attn.bias": "pytorch_model-00002-of-00002.bin",
512
- "transformer.h.47.attn.c_attn.weight": "pytorch_model-00002-of-00002.bin",
513
- "transformer.h.47.attn.c_proj.bias": "pytorch_model-00002-of-00002.bin",
514
- "transformer.h.47.attn.c_proj.weight": "pytorch_model-00002-of-00002.bin",
515
- "transformer.h.47.ln_1.bias": "pytorch_model-00002-of-00002.bin",
516
- "transformer.h.47.ln_1.weight": "pytorch_model-00002-of-00002.bin",
517
- "transformer.h.47.ln_2.bias": "pytorch_model-00002-of-00002.bin",
518
- "transformer.h.47.ln_2.weight": "pytorch_model-00002-of-00002.bin",
519
- "transformer.h.47.mlp.c_fc.bias": "pytorch_model-00002-of-00002.bin",
520
- "transformer.h.47.mlp.c_fc.weight": "pytorch_model-00002-of-00002.bin",
521
- "transformer.h.47.mlp.c_proj.bias": "pytorch_model-00002-of-00002.bin",
522
- "transformer.h.47.mlp.c_proj.weight": "pytorch_model-00002-of-00002.bin",
523
- "transformer.h.5.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
524
- "transformer.h.5.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
525
- "transformer.h.5.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
526
- "transformer.h.5.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
527
- "transformer.h.5.ln_1.bias": "pytorch_model-00001-of-00002.bin",
528
- "transformer.h.5.ln_1.weight": "pytorch_model-00001-of-00002.bin",
529
- "transformer.h.5.ln_2.bias": "pytorch_model-00001-of-00002.bin",
530
- "transformer.h.5.ln_2.weight": "pytorch_model-00001-of-00002.bin",
531
- "transformer.h.5.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
532
- "transformer.h.5.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
533
- "transformer.h.5.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
534
- "transformer.h.5.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
535
- "transformer.h.6.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
536
- "transformer.h.6.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
537
- "transformer.h.6.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
538
- "transformer.h.6.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
539
- "transformer.h.6.ln_1.bias": "pytorch_model-00001-of-00002.bin",
540
- "transformer.h.6.ln_1.weight": "pytorch_model-00001-of-00002.bin",
541
- "transformer.h.6.ln_2.bias": "pytorch_model-00001-of-00002.bin",
542
- "transformer.h.6.ln_2.weight": "pytorch_model-00001-of-00002.bin",
543
- "transformer.h.6.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
544
- "transformer.h.6.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
545
- "transformer.h.6.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
546
- "transformer.h.6.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
547
- "transformer.h.7.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
548
- "transformer.h.7.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
549
- "transformer.h.7.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
550
- "transformer.h.7.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
551
- "transformer.h.7.ln_1.bias": "pytorch_model-00001-of-00002.bin",
552
- "transformer.h.7.ln_1.weight": "pytorch_model-00001-of-00002.bin",
553
- "transformer.h.7.ln_2.bias": "pytorch_model-00001-of-00002.bin",
554
- "transformer.h.7.ln_2.weight": "pytorch_model-00001-of-00002.bin",
555
- "transformer.h.7.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
556
- "transformer.h.7.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
557
- "transformer.h.7.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
558
- "transformer.h.7.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
559
- "transformer.h.8.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
560
- "transformer.h.8.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
561
- "transformer.h.8.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
562
- "transformer.h.8.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
563
- "transformer.h.8.ln_1.bias": "pytorch_model-00001-of-00002.bin",
564
- "transformer.h.8.ln_1.weight": "pytorch_model-00001-of-00002.bin",
565
- "transformer.h.8.ln_2.bias": "pytorch_model-00001-of-00002.bin",
566
- "transformer.h.8.ln_2.weight": "pytorch_model-00001-of-00002.bin",
567
- "transformer.h.8.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
568
- "transformer.h.8.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
569
- "transformer.h.8.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
570
- "transformer.h.8.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
571
- "transformer.h.9.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
572
- "transformer.h.9.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
573
- "transformer.h.9.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
574
- "transformer.h.9.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
575
- "transformer.h.9.ln_1.bias": "pytorch_model-00001-of-00002.bin",
576
- "transformer.h.9.ln_1.weight": "pytorch_model-00001-of-00002.bin",
577
- "transformer.h.9.ln_2.bias": "pytorch_model-00001-of-00002.bin",
578
- "transformer.h.9.ln_2.weight": "pytorch_model-00001-of-00002.bin",
579
- "transformer.h.9.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
580
- "transformer.h.9.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
581
- "transformer.h.9.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
582
- "transformer.h.9.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
583
- "transformer.ln_f.bias": "pytorch_model-00002-of-00002.bin",
584
- "transformer.ln_f.weight": "pytorch_model-00002-of-00002.bin",
585
- "transformer.wpe.weight": "pytorch_model-00001-of-00002.bin",
586
- "transformer.wte.weight": "pytorch_model-00001-of-00002.bin"
587
- }
588
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
gpt2-xl-pt/checkpoint-120000/rng_state_0.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:08dcc92d5b11f0bb0ae012551fee899b614583a4eef99c2f86552e01ece3bfea
3
- size 15024
 
 
 
 
gpt2-xl-pt/checkpoint-120000/rng_state_1.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:84529c0c1528b9c7664233dfecb5436d7fa369072617ab308d6b5976fe5a40f4
3
- size 15024
 
 
 
 
gpt2-xl-pt/checkpoint-120000/rng_state_2.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:11c71f59f385f018d61cfa888e2f13b59430b9c1efd121c55870ee4832639c35
3
- size 15024
 
 
 
 
gpt2-xl-pt/checkpoint-120000/rng_state_3.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:3a08a04e552b23078e00b9380dd9d2ed36eb9bb524e5d64056518d982235288b
3
- size 15024
 
 
 
 
gpt2-xl-pt/checkpoint-120000/scheduler.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:2173489f9f315292c7c9c49aae56528ab60b0229c1e1e1fba1e26464b44e85cf
3
- size 1064
 
 
 
 
gpt2-xl-pt/checkpoint-120000/special_tokens_map.json DELETED
@@ -1,8 +0,0 @@
1
- {
2
- "bos_token": "<|endoftext|>",
3
- "eos_token": "<|endoftext|>",
4
- "mask_token": "------------",
5
- "pad_token": "<|endoftext|>",
6
- "sep_token": "======",
7
- "unk_token": "<|endoftext|>"
8
- }
 
 
 
 
 
 
 
 
 
gpt2-xl-pt/checkpoint-120000/tokenizer.json DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:1fe93b6152957cf9cfd6d89002467f789ce8b3f3e000b3a2edf27c808ddd0b9e
3
- size 3557680
 
 
 
 
gpt2-xl-pt/checkpoint-120000/tokenizer_config.json DELETED
@@ -1,26 +0,0 @@
1
- {
2
- "add_prefix_space": false,
3
- "added_tokens_decoder": {
4
- "50256": {
5
- "content": "<|endoftext|>",
6
- "lstrip": false,
7
- "normalized": true,
8
- "rstrip": false,
9
- "single_word": false,
10
- "special": true
11
- }
12
- },
13
- "bos_token": "<|endoftext|>",
14
- "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ system_message }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ content }}{% elif message['role'] == 'assistant' %}{{ content }}{% endif %}{% endfor %}",
15
- "clean_up_tokenization_spaces": false,
16
- "eos_token": "<|endoftext|>",
17
- "extra_special_tokens": {},
18
- "mask_token": "------------",
19
- "model_max_length": 1024,
20
- "pad_token": "<|endoftext|>",
21
- "padding_side": "right",
22
- "sep_token": "======",
23
- "split_special_tokens": false,
24
- "tokenizer_class": "GPT2Tokenizer",
25
- "unk_token": "<|endoftext|>"
26
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
gpt2-xl-pt/checkpoint-120000/trainer_state.json DELETED
The diff for this file is too large to render. See raw diff
 
gpt2-xl-pt/checkpoint-120000/training_args.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:e7d391756dd1f30115e58d744bf5706a5885cd4242b9ada8b6479c16bd95ed9e
3
- size 5560
 
 
 
 
gpt2-xl-pt/checkpoint-120000/vocab.json DELETED
The diff for this file is too large to render. See raw diff
 
gpt2-xl-pt/checkpoint-240000/config.json DELETED
@@ -1,39 +0,0 @@
1
- {
2
- "activation_function": "gelu_new",
3
- "architectures": [
4
- "GPT2LMHeadModel"
5
- ],
6
- "attn_pdrop": 0.1,
7
- "bos_token_id": 50256,
8
- "embd_pdrop": 0.1,
9
- "eos_token_id": 50256,
10
- "initializer_range": 0.02,
11
- "layer_norm_epsilon": 1e-05,
12
- "model_type": "gpt2",
13
- "n_ctx": 1024,
14
- "n_embd": 1600,
15
- "n_head": 25,
16
- "n_inner": null,
17
- "n_layer": 48,
18
- "n_positions": 1024,
19
- "output_past": true,
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": "4.50.3",
37
- "use_cache": false,
38
- "vocab_size": 50257
39
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
gpt2-xl-pt/checkpoint-240000/generation_config.json DELETED
@@ -1,6 +0,0 @@
1
- {
2
- "_from_model_config": true,
3
- "bos_token_id": 50256,
4
- "eos_token_id": 50256,
5
- "transformers_version": "4.50.3"
6
- }
 
 
 
 
 
 
 
gpt2-xl-pt/checkpoint-240000/merges.txt DELETED
The diff for this file is too large to render. See raw diff
 
gpt2-xl-pt/checkpoint-240000/optimizer.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:f8d8923b983cc84ce57677a5f9611fab62e59254aa1d201882a294121757801a
3
- size 12461385454
 
 
 
 
gpt2-xl-pt/checkpoint-240000/pytorch_model-00001-of-00002.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:daa5488f6634f1405340d2d5d1f5fc1320e6400e5355c4088d373dc879c0efa8
3
- size 4959990818
 
 
 
 
gpt2-xl-pt/checkpoint-240000/pytorch_model-00002-of-00002.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:5ee97b8fd44d6de06e13556226ca70dccf301b37082094343e54ad39ae7247cd
3
- size 1270653818
 
 
 
 
gpt2-xl-pt/checkpoint-240000/pytorch_model.bin.index.json DELETED
@@ -1,588 +0,0 @@
1
- {
2
- "metadata": {
3
- "total_size": 6230444800
4
- },
5
- "weight_map": {
6
- "lm_head.weight": "pytorch_model-00001-of-00002.bin",
7
- "transformer.h.0.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
8
- "transformer.h.0.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
9
- "transformer.h.0.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
10
- "transformer.h.0.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
11
- "transformer.h.0.ln_1.bias": "pytorch_model-00001-of-00002.bin",
12
- "transformer.h.0.ln_1.weight": "pytorch_model-00001-of-00002.bin",
13
- "transformer.h.0.ln_2.bias": "pytorch_model-00001-of-00002.bin",
14
- "transformer.h.0.ln_2.weight": "pytorch_model-00001-of-00002.bin",
15
- "transformer.h.0.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
16
- "transformer.h.0.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
17
- "transformer.h.0.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
18
- "transformer.h.0.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
19
- "transformer.h.1.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
20
- "transformer.h.1.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
21
- "transformer.h.1.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
22
- "transformer.h.1.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
23
- "transformer.h.1.ln_1.bias": "pytorch_model-00001-of-00002.bin",
24
- "transformer.h.1.ln_1.weight": "pytorch_model-00001-of-00002.bin",
25
- "transformer.h.1.ln_2.bias": "pytorch_model-00001-of-00002.bin",
26
- "transformer.h.1.ln_2.weight": "pytorch_model-00001-of-00002.bin",
27
- "transformer.h.1.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
28
- "transformer.h.1.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
29
- "transformer.h.1.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
30
- "transformer.h.1.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
31
- "transformer.h.10.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
32
- "transformer.h.10.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
33
- "transformer.h.10.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
34
- "transformer.h.10.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
35
- "transformer.h.10.ln_1.bias": "pytorch_model-00001-of-00002.bin",
36
- "transformer.h.10.ln_1.weight": "pytorch_model-00001-of-00002.bin",
37
- "transformer.h.10.ln_2.bias": "pytorch_model-00001-of-00002.bin",
38
- "transformer.h.10.ln_2.weight": "pytorch_model-00001-of-00002.bin",
39
- "transformer.h.10.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
40
- "transformer.h.10.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
41
- "transformer.h.10.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
42
- "transformer.h.10.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
43
- "transformer.h.11.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
44
- "transformer.h.11.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
45
- "transformer.h.11.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
46
- "transformer.h.11.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
47
- "transformer.h.11.ln_1.bias": "pytorch_model-00001-of-00002.bin",
48
- "transformer.h.11.ln_1.weight": "pytorch_model-00001-of-00002.bin",
49
- "transformer.h.11.ln_2.bias": "pytorch_model-00001-of-00002.bin",
50
- "transformer.h.11.ln_2.weight": "pytorch_model-00001-of-00002.bin",
51
- "transformer.h.11.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
52
- "transformer.h.11.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
53
- "transformer.h.11.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
54
- "transformer.h.11.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
55
- "transformer.h.12.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
56
- "transformer.h.12.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
57
- "transformer.h.12.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
58
- "transformer.h.12.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
59
- "transformer.h.12.ln_1.bias": "pytorch_model-00001-of-00002.bin",
60
- "transformer.h.12.ln_1.weight": "pytorch_model-00001-of-00002.bin",
61
- "transformer.h.12.ln_2.bias": "pytorch_model-00001-of-00002.bin",
62
- "transformer.h.12.ln_2.weight": "pytorch_model-00001-of-00002.bin",
63
- "transformer.h.12.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
64
- "transformer.h.12.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
65
- "transformer.h.12.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
66
- "transformer.h.12.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
67
- "transformer.h.13.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
68
- "transformer.h.13.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
69
- "transformer.h.13.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
70
- "transformer.h.13.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
71
- "transformer.h.13.ln_1.bias": "pytorch_model-00001-of-00002.bin",
72
- "transformer.h.13.ln_1.weight": "pytorch_model-00001-of-00002.bin",
73
- "transformer.h.13.ln_2.bias": "pytorch_model-00001-of-00002.bin",
74
- "transformer.h.13.ln_2.weight": "pytorch_model-00001-of-00002.bin",
75
- "transformer.h.13.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
76
- "transformer.h.13.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
77
- "transformer.h.13.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
78
- "transformer.h.13.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
79
- "transformer.h.14.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
80
- "transformer.h.14.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
81
- "transformer.h.14.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
82
- "transformer.h.14.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
83
- "transformer.h.14.ln_1.bias": "pytorch_model-00001-of-00002.bin",
84
- "transformer.h.14.ln_1.weight": "pytorch_model-00001-of-00002.bin",
85
- "transformer.h.14.ln_2.bias": "pytorch_model-00001-of-00002.bin",
86
- "transformer.h.14.ln_2.weight": "pytorch_model-00001-of-00002.bin",
87
- "transformer.h.14.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
88
- "transformer.h.14.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
89
- "transformer.h.14.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
90
- "transformer.h.14.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
91
- "transformer.h.15.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
92
- "transformer.h.15.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
93
- "transformer.h.15.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
94
- "transformer.h.15.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
95
- "transformer.h.15.ln_1.bias": "pytorch_model-00001-of-00002.bin",
96
- "transformer.h.15.ln_1.weight": "pytorch_model-00001-of-00002.bin",
97
- "transformer.h.15.ln_2.bias": "pytorch_model-00001-of-00002.bin",
98
- "transformer.h.15.ln_2.weight": "pytorch_model-00001-of-00002.bin",
99
- "transformer.h.15.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
100
- "transformer.h.15.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
101
- "transformer.h.15.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
102
- "transformer.h.15.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
103
- "transformer.h.16.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
104
- "transformer.h.16.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
105
- "transformer.h.16.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
106
- "transformer.h.16.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
107
- "transformer.h.16.ln_1.bias": "pytorch_model-00001-of-00002.bin",
108
- "transformer.h.16.ln_1.weight": "pytorch_model-00001-of-00002.bin",
109
- "transformer.h.16.ln_2.bias": "pytorch_model-00001-of-00002.bin",
110
- "transformer.h.16.ln_2.weight": "pytorch_model-00001-of-00002.bin",
111
- "transformer.h.16.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
112
- "transformer.h.16.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
113
- "transformer.h.16.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
114
- "transformer.h.16.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
115
- "transformer.h.17.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
116
- "transformer.h.17.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
117
- "transformer.h.17.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
118
- "transformer.h.17.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
119
- "transformer.h.17.ln_1.bias": "pytorch_model-00001-of-00002.bin",
120
- "transformer.h.17.ln_1.weight": "pytorch_model-00001-of-00002.bin",
121
- "transformer.h.17.ln_2.bias": "pytorch_model-00001-of-00002.bin",
122
- "transformer.h.17.ln_2.weight": "pytorch_model-00001-of-00002.bin",
123
- "transformer.h.17.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
124
- "transformer.h.17.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
125
- "transformer.h.17.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
126
- "transformer.h.17.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
127
- "transformer.h.18.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
128
- "transformer.h.18.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
129
- "transformer.h.18.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
130
- "transformer.h.18.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
131
- "transformer.h.18.ln_1.bias": "pytorch_model-00001-of-00002.bin",
132
- "transformer.h.18.ln_1.weight": "pytorch_model-00001-of-00002.bin",
133
- "transformer.h.18.ln_2.bias": "pytorch_model-00001-of-00002.bin",
134
- "transformer.h.18.ln_2.weight": "pytorch_model-00001-of-00002.bin",
135
- "transformer.h.18.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
136
- "transformer.h.18.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
137
- "transformer.h.18.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
138
- "transformer.h.18.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
139
- "transformer.h.19.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
140
- "transformer.h.19.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
141
- "transformer.h.19.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
142
- "transformer.h.19.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
143
- "transformer.h.19.ln_1.bias": "pytorch_model-00001-of-00002.bin",
144
- "transformer.h.19.ln_1.weight": "pytorch_model-00001-of-00002.bin",
145
- "transformer.h.19.ln_2.bias": "pytorch_model-00001-of-00002.bin",
146
- "transformer.h.19.ln_2.weight": "pytorch_model-00001-of-00002.bin",
147
- "transformer.h.19.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
148
- "transformer.h.19.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
149
- "transformer.h.19.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
150
- "transformer.h.19.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
151
- "transformer.h.2.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
152
- "transformer.h.2.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
153
- "transformer.h.2.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
154
- "transformer.h.2.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
155
- "transformer.h.2.ln_1.bias": "pytorch_model-00001-of-00002.bin",
156
- "transformer.h.2.ln_1.weight": "pytorch_model-00001-of-00002.bin",
157
- "transformer.h.2.ln_2.bias": "pytorch_model-00001-of-00002.bin",
158
- "transformer.h.2.ln_2.weight": "pytorch_model-00001-of-00002.bin",
159
- "transformer.h.2.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
160
- "transformer.h.2.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
161
- "transformer.h.2.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
162
- "transformer.h.2.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
163
- "transformer.h.20.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
164
- "transformer.h.20.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
165
- "transformer.h.20.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
166
- "transformer.h.20.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
167
- "transformer.h.20.ln_1.bias": "pytorch_model-00001-of-00002.bin",
168
- "transformer.h.20.ln_1.weight": "pytorch_model-00001-of-00002.bin",
169
- "transformer.h.20.ln_2.bias": "pytorch_model-00001-of-00002.bin",
170
- "transformer.h.20.ln_2.weight": "pytorch_model-00001-of-00002.bin",
171
- "transformer.h.20.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
172
- "transformer.h.20.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
173
- "transformer.h.20.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
174
- "transformer.h.20.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
175
- "transformer.h.21.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
176
- "transformer.h.21.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
177
- "transformer.h.21.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
178
- "transformer.h.21.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
179
- "transformer.h.21.ln_1.bias": "pytorch_model-00001-of-00002.bin",
180
- "transformer.h.21.ln_1.weight": "pytorch_model-00001-of-00002.bin",
181
- "transformer.h.21.ln_2.bias": "pytorch_model-00001-of-00002.bin",
182
- "transformer.h.21.ln_2.weight": "pytorch_model-00001-of-00002.bin",
183
- "transformer.h.21.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
184
- "transformer.h.21.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
185
- "transformer.h.21.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
186
- "transformer.h.21.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
187
- "transformer.h.22.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
188
- "transformer.h.22.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
189
- "transformer.h.22.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
190
- "transformer.h.22.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
191
- "transformer.h.22.ln_1.bias": "pytorch_model-00001-of-00002.bin",
192
- "transformer.h.22.ln_1.weight": "pytorch_model-00001-of-00002.bin",
193
- "transformer.h.22.ln_2.bias": "pytorch_model-00001-of-00002.bin",
194
- "transformer.h.22.ln_2.weight": "pytorch_model-00001-of-00002.bin",
195
- "transformer.h.22.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
196
- "transformer.h.22.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
197
- "transformer.h.22.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
198
- "transformer.h.22.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
199
- "transformer.h.23.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
200
- "transformer.h.23.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
201
- "transformer.h.23.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
202
- "transformer.h.23.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
203
- "transformer.h.23.ln_1.bias": "pytorch_model-00001-of-00002.bin",
204
- "transformer.h.23.ln_1.weight": "pytorch_model-00001-of-00002.bin",
205
- "transformer.h.23.ln_2.bias": "pytorch_model-00001-of-00002.bin",
206
- "transformer.h.23.ln_2.weight": "pytorch_model-00001-of-00002.bin",
207
- "transformer.h.23.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
208
- "transformer.h.23.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
209
- "transformer.h.23.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
210
- "transformer.h.23.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
211
- "transformer.h.24.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
212
- "transformer.h.24.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
213
- "transformer.h.24.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
214
- "transformer.h.24.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
215
- "transformer.h.24.ln_1.bias": "pytorch_model-00001-of-00002.bin",
216
- "transformer.h.24.ln_1.weight": "pytorch_model-00001-of-00002.bin",
217
- "transformer.h.24.ln_2.bias": "pytorch_model-00001-of-00002.bin",
218
- "transformer.h.24.ln_2.weight": "pytorch_model-00001-of-00002.bin",
219
- "transformer.h.24.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
220
- "transformer.h.24.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
221
- "transformer.h.24.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
222
- "transformer.h.24.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
223
- "transformer.h.25.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
224
- "transformer.h.25.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
225
- "transformer.h.25.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
226
- "transformer.h.25.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
227
- "transformer.h.25.ln_1.bias": "pytorch_model-00001-of-00002.bin",
228
- "transformer.h.25.ln_1.weight": "pytorch_model-00001-of-00002.bin",
229
- "transformer.h.25.ln_2.bias": "pytorch_model-00001-of-00002.bin",
230
- "transformer.h.25.ln_2.weight": "pytorch_model-00001-of-00002.bin",
231
- "transformer.h.25.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
232
- "transformer.h.25.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
233
- "transformer.h.25.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
234
- "transformer.h.25.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
235
- "transformer.h.26.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
236
- "transformer.h.26.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
237
- "transformer.h.26.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
238
- "transformer.h.26.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
239
- "transformer.h.26.ln_1.bias": "pytorch_model-00001-of-00002.bin",
240
- "transformer.h.26.ln_1.weight": "pytorch_model-00001-of-00002.bin",
241
- "transformer.h.26.ln_2.bias": "pytorch_model-00001-of-00002.bin",
242
- "transformer.h.26.ln_2.weight": "pytorch_model-00001-of-00002.bin",
243
- "transformer.h.26.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
244
- "transformer.h.26.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
245
- "transformer.h.26.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
246
- "transformer.h.26.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
247
- "transformer.h.27.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
248
- "transformer.h.27.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
249
- "transformer.h.27.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
250
- "transformer.h.27.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
251
- "transformer.h.27.ln_1.bias": "pytorch_model-00001-of-00002.bin",
252
- "transformer.h.27.ln_1.weight": "pytorch_model-00001-of-00002.bin",
253
- "transformer.h.27.ln_2.bias": "pytorch_model-00001-of-00002.bin",
254
- "transformer.h.27.ln_2.weight": "pytorch_model-00001-of-00002.bin",
255
- "transformer.h.27.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
256
- "transformer.h.27.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
257
- "transformer.h.27.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
258
- "transformer.h.27.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
259
- "transformer.h.28.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
260
- "transformer.h.28.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
261
- "transformer.h.28.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
262
- "transformer.h.28.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
263
- "transformer.h.28.ln_1.bias": "pytorch_model-00001-of-00002.bin",
264
- "transformer.h.28.ln_1.weight": "pytorch_model-00001-of-00002.bin",
265
- "transformer.h.28.ln_2.bias": "pytorch_model-00001-of-00002.bin",
266
- "transformer.h.28.ln_2.weight": "pytorch_model-00001-of-00002.bin",
267
- "transformer.h.28.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
268
- "transformer.h.28.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
269
- "transformer.h.28.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
270
- "transformer.h.28.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
271
- "transformer.h.29.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
272
- "transformer.h.29.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
273
- "transformer.h.29.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
274
- "transformer.h.29.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
275
- "transformer.h.29.ln_1.bias": "pytorch_model-00001-of-00002.bin",
276
- "transformer.h.29.ln_1.weight": "pytorch_model-00001-of-00002.bin",
277
- "transformer.h.29.ln_2.bias": "pytorch_model-00001-of-00002.bin",
278
- "transformer.h.29.ln_2.weight": "pytorch_model-00001-of-00002.bin",
279
- "transformer.h.29.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
280
- "transformer.h.29.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
281
- "transformer.h.29.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
282
- "transformer.h.29.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
283
- "transformer.h.3.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
284
- "transformer.h.3.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
285
- "transformer.h.3.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
286
- "transformer.h.3.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
287
- "transformer.h.3.ln_1.bias": "pytorch_model-00001-of-00002.bin",
288
- "transformer.h.3.ln_1.weight": "pytorch_model-00001-of-00002.bin",
289
- "transformer.h.3.ln_2.bias": "pytorch_model-00001-of-00002.bin",
290
- "transformer.h.3.ln_2.weight": "pytorch_model-00001-of-00002.bin",
291
- "transformer.h.3.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
292
- "transformer.h.3.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
293
- "transformer.h.3.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
294
- "transformer.h.3.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
295
- "transformer.h.30.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
296
- "transformer.h.30.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
297
- "transformer.h.30.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
298
- "transformer.h.30.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
299
- "transformer.h.30.ln_1.bias": "pytorch_model-00001-of-00002.bin",
300
- "transformer.h.30.ln_1.weight": "pytorch_model-00001-of-00002.bin",
301
- "transformer.h.30.ln_2.bias": "pytorch_model-00001-of-00002.bin",
302
- "transformer.h.30.ln_2.weight": "pytorch_model-00001-of-00002.bin",
303
- "transformer.h.30.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
304
- "transformer.h.30.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
305
- "transformer.h.30.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
306
- "transformer.h.30.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
307
- "transformer.h.31.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
308
- "transformer.h.31.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
309
- "transformer.h.31.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
310
- "transformer.h.31.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
311
- "transformer.h.31.ln_1.bias": "pytorch_model-00001-of-00002.bin",
312
- "transformer.h.31.ln_1.weight": "pytorch_model-00001-of-00002.bin",
313
- "transformer.h.31.ln_2.bias": "pytorch_model-00001-of-00002.bin",
314
- "transformer.h.31.ln_2.weight": "pytorch_model-00001-of-00002.bin",
315
- "transformer.h.31.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
316
- "transformer.h.31.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
317
- "transformer.h.31.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
318
- "transformer.h.31.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
319
- "transformer.h.32.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
320
- "transformer.h.32.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
321
- "transformer.h.32.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
322
- "transformer.h.32.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
323
- "transformer.h.32.ln_1.bias": "pytorch_model-00001-of-00002.bin",
324
- "transformer.h.32.ln_1.weight": "pytorch_model-00001-of-00002.bin",
325
- "transformer.h.32.ln_2.bias": "pytorch_model-00001-of-00002.bin",
326
- "transformer.h.32.ln_2.weight": "pytorch_model-00001-of-00002.bin",
327
- "transformer.h.32.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
328
- "transformer.h.32.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
329
- "transformer.h.32.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
330
- "transformer.h.32.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
331
- "transformer.h.33.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
332
- "transformer.h.33.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
333
- "transformer.h.33.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
334
- "transformer.h.33.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
335
- "transformer.h.33.ln_1.bias": "pytorch_model-00001-of-00002.bin",
336
- "transformer.h.33.ln_1.weight": "pytorch_model-00001-of-00002.bin",
337
- "transformer.h.33.ln_2.bias": "pytorch_model-00001-of-00002.bin",
338
- "transformer.h.33.ln_2.weight": "pytorch_model-00001-of-00002.bin",
339
- "transformer.h.33.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
340
- "transformer.h.33.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
341
- "transformer.h.33.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
342
- "transformer.h.33.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
343
- "transformer.h.34.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
344
- "transformer.h.34.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
345
- "transformer.h.34.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
346
- "transformer.h.34.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
347
- "transformer.h.34.ln_1.bias": "pytorch_model-00001-of-00002.bin",
348
- "transformer.h.34.ln_1.weight": "pytorch_model-00001-of-00002.bin",
349
- "transformer.h.34.ln_2.bias": "pytorch_model-00001-of-00002.bin",
350
- "transformer.h.34.ln_2.weight": "pytorch_model-00001-of-00002.bin",
351
- "transformer.h.34.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
352
- "transformer.h.34.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
353
- "transformer.h.34.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
354
- "transformer.h.34.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
355
- "transformer.h.35.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
356
- "transformer.h.35.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
357
- "transformer.h.35.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
358
- "transformer.h.35.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
359
- "transformer.h.35.ln_1.bias": "pytorch_model-00001-of-00002.bin",
360
- "transformer.h.35.ln_1.weight": "pytorch_model-00001-of-00002.bin",
361
- "transformer.h.35.ln_2.bias": "pytorch_model-00001-of-00002.bin",
362
- "transformer.h.35.ln_2.weight": "pytorch_model-00001-of-00002.bin",
363
- "transformer.h.35.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
364
- "transformer.h.35.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
365
- "transformer.h.35.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
366
- "transformer.h.35.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
367
- "transformer.h.36.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
368
- "transformer.h.36.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
369
- "transformer.h.36.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
370
- "transformer.h.36.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
371
- "transformer.h.36.ln_1.bias": "pytorch_model-00001-of-00002.bin",
372
- "transformer.h.36.ln_1.weight": "pytorch_model-00001-of-00002.bin",
373
- "transformer.h.36.ln_2.bias": "pytorch_model-00001-of-00002.bin",
374
- "transformer.h.36.ln_2.weight": "pytorch_model-00001-of-00002.bin",
375
- "transformer.h.36.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
376
- "transformer.h.36.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
377
- "transformer.h.36.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
378
- "transformer.h.36.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
379
- "transformer.h.37.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
380
- "transformer.h.37.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
381
- "transformer.h.37.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
382
- "transformer.h.37.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
383
- "transformer.h.37.ln_1.bias": "pytorch_model-00001-of-00002.bin",
384
- "transformer.h.37.ln_1.weight": "pytorch_model-00001-of-00002.bin",
385
- "transformer.h.37.ln_2.bias": "pytorch_model-00001-of-00002.bin",
386
- "transformer.h.37.ln_2.weight": "pytorch_model-00001-of-00002.bin",
387
- "transformer.h.37.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
388
- "transformer.h.37.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
389
- "transformer.h.37.mlp.c_proj.bias": "pytorch_model-00002-of-00002.bin",
390
- "transformer.h.37.mlp.c_proj.weight": "pytorch_model-00002-of-00002.bin",
391
- "transformer.h.38.attn.c_attn.bias": "pytorch_model-00002-of-00002.bin",
392
- "transformer.h.38.attn.c_attn.weight": "pytorch_model-00002-of-00002.bin",
393
- "transformer.h.38.attn.c_proj.bias": "pytorch_model-00002-of-00002.bin",
394
- "transformer.h.38.attn.c_proj.weight": "pytorch_model-00002-of-00002.bin",
395
- "transformer.h.38.ln_1.bias": "pytorch_model-00002-of-00002.bin",
396
- "transformer.h.38.ln_1.weight": "pytorch_model-00002-of-00002.bin",
397
- "transformer.h.38.ln_2.bias": "pytorch_model-00002-of-00002.bin",
398
- "transformer.h.38.ln_2.weight": "pytorch_model-00002-of-00002.bin",
399
- "transformer.h.38.mlp.c_fc.bias": "pytorch_model-00002-of-00002.bin",
400
- "transformer.h.38.mlp.c_fc.weight": "pytorch_model-00002-of-00002.bin",
401
- "transformer.h.38.mlp.c_proj.bias": "pytorch_model-00002-of-00002.bin",
402
- "transformer.h.38.mlp.c_proj.weight": "pytorch_model-00002-of-00002.bin",
403
- "transformer.h.39.attn.c_attn.bias": "pytorch_model-00002-of-00002.bin",
404
- "transformer.h.39.attn.c_attn.weight": "pytorch_model-00002-of-00002.bin",
405
- "transformer.h.39.attn.c_proj.bias": "pytorch_model-00002-of-00002.bin",
406
- "transformer.h.39.attn.c_proj.weight": "pytorch_model-00002-of-00002.bin",
407
- "transformer.h.39.ln_1.bias": "pytorch_model-00002-of-00002.bin",
408
- "transformer.h.39.ln_1.weight": "pytorch_model-00002-of-00002.bin",
409
- "transformer.h.39.ln_2.bias": "pytorch_model-00002-of-00002.bin",
410
- "transformer.h.39.ln_2.weight": "pytorch_model-00002-of-00002.bin",
411
- "transformer.h.39.mlp.c_fc.bias": "pytorch_model-00002-of-00002.bin",
412
- "transformer.h.39.mlp.c_fc.weight": "pytorch_model-00002-of-00002.bin",
413
- "transformer.h.39.mlp.c_proj.bias": "pytorch_model-00002-of-00002.bin",
414
- "transformer.h.39.mlp.c_proj.weight": "pytorch_model-00002-of-00002.bin",
415
- "transformer.h.4.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
416
- "transformer.h.4.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
417
- "transformer.h.4.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
418
- "transformer.h.4.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
419
- "transformer.h.4.ln_1.bias": "pytorch_model-00001-of-00002.bin",
420
- "transformer.h.4.ln_1.weight": "pytorch_model-00001-of-00002.bin",
421
- "transformer.h.4.ln_2.bias": "pytorch_model-00001-of-00002.bin",
422
- "transformer.h.4.ln_2.weight": "pytorch_model-00001-of-00002.bin",
423
- "transformer.h.4.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
424
- "transformer.h.4.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
425
- "transformer.h.4.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
426
- "transformer.h.4.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
427
- "transformer.h.40.attn.c_attn.bias": "pytorch_model-00002-of-00002.bin",
428
- "transformer.h.40.attn.c_attn.weight": "pytorch_model-00002-of-00002.bin",
429
- "transformer.h.40.attn.c_proj.bias": "pytorch_model-00002-of-00002.bin",
430
- "transformer.h.40.attn.c_proj.weight": "pytorch_model-00002-of-00002.bin",
431
- "transformer.h.40.ln_1.bias": "pytorch_model-00002-of-00002.bin",
432
- "transformer.h.40.ln_1.weight": "pytorch_model-00002-of-00002.bin",
433
- "transformer.h.40.ln_2.bias": "pytorch_model-00002-of-00002.bin",
434
- "transformer.h.40.ln_2.weight": "pytorch_model-00002-of-00002.bin",
435
- "transformer.h.40.mlp.c_fc.bias": "pytorch_model-00002-of-00002.bin",
436
- "transformer.h.40.mlp.c_fc.weight": "pytorch_model-00002-of-00002.bin",
437
- "transformer.h.40.mlp.c_proj.bias": "pytorch_model-00002-of-00002.bin",
438
- "transformer.h.40.mlp.c_proj.weight": "pytorch_model-00002-of-00002.bin",
439
- "transformer.h.41.attn.c_attn.bias": "pytorch_model-00002-of-00002.bin",
440
- "transformer.h.41.attn.c_attn.weight": "pytorch_model-00002-of-00002.bin",
441
- "transformer.h.41.attn.c_proj.bias": "pytorch_model-00002-of-00002.bin",
442
- "transformer.h.41.attn.c_proj.weight": "pytorch_model-00002-of-00002.bin",
443
- "transformer.h.41.ln_1.bias": "pytorch_model-00002-of-00002.bin",
444
- "transformer.h.41.ln_1.weight": "pytorch_model-00002-of-00002.bin",
445
- "transformer.h.41.ln_2.bias": "pytorch_model-00002-of-00002.bin",
446
- "transformer.h.41.ln_2.weight": "pytorch_model-00002-of-00002.bin",
447
- "transformer.h.41.mlp.c_fc.bias": "pytorch_model-00002-of-00002.bin",
448
- "transformer.h.41.mlp.c_fc.weight": "pytorch_model-00002-of-00002.bin",
449
- "transformer.h.41.mlp.c_proj.bias": "pytorch_model-00002-of-00002.bin",
450
- "transformer.h.41.mlp.c_proj.weight": "pytorch_model-00002-of-00002.bin",
451
- "transformer.h.42.attn.c_attn.bias": "pytorch_model-00002-of-00002.bin",
452
- "transformer.h.42.attn.c_attn.weight": "pytorch_model-00002-of-00002.bin",
453
- "transformer.h.42.attn.c_proj.bias": "pytorch_model-00002-of-00002.bin",
454
- "transformer.h.42.attn.c_proj.weight": "pytorch_model-00002-of-00002.bin",
455
- "transformer.h.42.ln_1.bias": "pytorch_model-00002-of-00002.bin",
456
- "transformer.h.42.ln_1.weight": "pytorch_model-00002-of-00002.bin",
457
- "transformer.h.42.ln_2.bias": "pytorch_model-00002-of-00002.bin",
458
- "transformer.h.42.ln_2.weight": "pytorch_model-00002-of-00002.bin",
459
- "transformer.h.42.mlp.c_fc.bias": "pytorch_model-00002-of-00002.bin",
460
- "transformer.h.42.mlp.c_fc.weight": "pytorch_model-00002-of-00002.bin",
461
- "transformer.h.42.mlp.c_proj.bias": "pytorch_model-00002-of-00002.bin",
462
- "transformer.h.42.mlp.c_proj.weight": "pytorch_model-00002-of-00002.bin",
463
- "transformer.h.43.attn.c_attn.bias": "pytorch_model-00002-of-00002.bin",
464
- "transformer.h.43.attn.c_attn.weight": "pytorch_model-00002-of-00002.bin",
465
- "transformer.h.43.attn.c_proj.bias": "pytorch_model-00002-of-00002.bin",
466
- "transformer.h.43.attn.c_proj.weight": "pytorch_model-00002-of-00002.bin",
467
- "transformer.h.43.ln_1.bias": "pytorch_model-00002-of-00002.bin",
468
- "transformer.h.43.ln_1.weight": "pytorch_model-00002-of-00002.bin",
469
- "transformer.h.43.ln_2.bias": "pytorch_model-00002-of-00002.bin",
470
- "transformer.h.43.ln_2.weight": "pytorch_model-00002-of-00002.bin",
471
- "transformer.h.43.mlp.c_fc.bias": "pytorch_model-00002-of-00002.bin",
472
- "transformer.h.43.mlp.c_fc.weight": "pytorch_model-00002-of-00002.bin",
473
- "transformer.h.43.mlp.c_proj.bias": "pytorch_model-00002-of-00002.bin",
474
- "transformer.h.43.mlp.c_proj.weight": "pytorch_model-00002-of-00002.bin",
475
- "transformer.h.44.attn.c_attn.bias": "pytorch_model-00002-of-00002.bin",
476
- "transformer.h.44.attn.c_attn.weight": "pytorch_model-00002-of-00002.bin",
477
- "transformer.h.44.attn.c_proj.bias": "pytorch_model-00002-of-00002.bin",
478
- "transformer.h.44.attn.c_proj.weight": "pytorch_model-00002-of-00002.bin",
479
- "transformer.h.44.ln_1.bias": "pytorch_model-00002-of-00002.bin",
480
- "transformer.h.44.ln_1.weight": "pytorch_model-00002-of-00002.bin",
481
- "transformer.h.44.ln_2.bias": "pytorch_model-00002-of-00002.bin",
482
- "transformer.h.44.ln_2.weight": "pytorch_model-00002-of-00002.bin",
483
- "transformer.h.44.mlp.c_fc.bias": "pytorch_model-00002-of-00002.bin",
484
- "transformer.h.44.mlp.c_fc.weight": "pytorch_model-00002-of-00002.bin",
485
- "transformer.h.44.mlp.c_proj.bias": "pytorch_model-00002-of-00002.bin",
486
- "transformer.h.44.mlp.c_proj.weight": "pytorch_model-00002-of-00002.bin",
487
- "transformer.h.45.attn.c_attn.bias": "pytorch_model-00002-of-00002.bin",
488
- "transformer.h.45.attn.c_attn.weight": "pytorch_model-00002-of-00002.bin",
489
- "transformer.h.45.attn.c_proj.bias": "pytorch_model-00002-of-00002.bin",
490
- "transformer.h.45.attn.c_proj.weight": "pytorch_model-00002-of-00002.bin",
491
- "transformer.h.45.ln_1.bias": "pytorch_model-00002-of-00002.bin",
492
- "transformer.h.45.ln_1.weight": "pytorch_model-00002-of-00002.bin",
493
- "transformer.h.45.ln_2.bias": "pytorch_model-00002-of-00002.bin",
494
- "transformer.h.45.ln_2.weight": "pytorch_model-00002-of-00002.bin",
495
- "transformer.h.45.mlp.c_fc.bias": "pytorch_model-00002-of-00002.bin",
496
- "transformer.h.45.mlp.c_fc.weight": "pytorch_model-00002-of-00002.bin",
497
- "transformer.h.45.mlp.c_proj.bias": "pytorch_model-00002-of-00002.bin",
498
- "transformer.h.45.mlp.c_proj.weight": "pytorch_model-00002-of-00002.bin",
499
- "transformer.h.46.attn.c_attn.bias": "pytorch_model-00002-of-00002.bin",
500
- "transformer.h.46.attn.c_attn.weight": "pytorch_model-00002-of-00002.bin",
501
- "transformer.h.46.attn.c_proj.bias": "pytorch_model-00002-of-00002.bin",
502
- "transformer.h.46.attn.c_proj.weight": "pytorch_model-00002-of-00002.bin",
503
- "transformer.h.46.ln_1.bias": "pytorch_model-00002-of-00002.bin",
504
- "transformer.h.46.ln_1.weight": "pytorch_model-00002-of-00002.bin",
505
- "transformer.h.46.ln_2.bias": "pytorch_model-00002-of-00002.bin",
506
- "transformer.h.46.ln_2.weight": "pytorch_model-00002-of-00002.bin",
507
- "transformer.h.46.mlp.c_fc.bias": "pytorch_model-00002-of-00002.bin",
508
- "transformer.h.46.mlp.c_fc.weight": "pytorch_model-00002-of-00002.bin",
509
- "transformer.h.46.mlp.c_proj.bias": "pytorch_model-00002-of-00002.bin",
510
- "transformer.h.46.mlp.c_proj.weight": "pytorch_model-00002-of-00002.bin",
511
- "transformer.h.47.attn.c_attn.bias": "pytorch_model-00002-of-00002.bin",
512
- "transformer.h.47.attn.c_attn.weight": "pytorch_model-00002-of-00002.bin",
513
- "transformer.h.47.attn.c_proj.bias": "pytorch_model-00002-of-00002.bin",
514
- "transformer.h.47.attn.c_proj.weight": "pytorch_model-00002-of-00002.bin",
515
- "transformer.h.47.ln_1.bias": "pytorch_model-00002-of-00002.bin",
516
- "transformer.h.47.ln_1.weight": "pytorch_model-00002-of-00002.bin",
517
- "transformer.h.47.ln_2.bias": "pytorch_model-00002-of-00002.bin",
518
- "transformer.h.47.ln_2.weight": "pytorch_model-00002-of-00002.bin",
519
- "transformer.h.47.mlp.c_fc.bias": "pytorch_model-00002-of-00002.bin",
520
- "transformer.h.47.mlp.c_fc.weight": "pytorch_model-00002-of-00002.bin",
521
- "transformer.h.47.mlp.c_proj.bias": "pytorch_model-00002-of-00002.bin",
522
- "transformer.h.47.mlp.c_proj.weight": "pytorch_model-00002-of-00002.bin",
523
- "transformer.h.5.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
524
- "transformer.h.5.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
525
- "transformer.h.5.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
526
- "transformer.h.5.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
527
- "transformer.h.5.ln_1.bias": "pytorch_model-00001-of-00002.bin",
528
- "transformer.h.5.ln_1.weight": "pytorch_model-00001-of-00002.bin",
529
- "transformer.h.5.ln_2.bias": "pytorch_model-00001-of-00002.bin",
530
- "transformer.h.5.ln_2.weight": "pytorch_model-00001-of-00002.bin",
531
- "transformer.h.5.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
532
- "transformer.h.5.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
533
- "transformer.h.5.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
534
- "transformer.h.5.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
535
- "transformer.h.6.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
536
- "transformer.h.6.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
537
- "transformer.h.6.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
538
- "transformer.h.6.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
539
- "transformer.h.6.ln_1.bias": "pytorch_model-00001-of-00002.bin",
540
- "transformer.h.6.ln_1.weight": "pytorch_model-00001-of-00002.bin",
541
- "transformer.h.6.ln_2.bias": "pytorch_model-00001-of-00002.bin",
542
- "transformer.h.6.ln_2.weight": "pytorch_model-00001-of-00002.bin",
543
- "transformer.h.6.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
544
- "transformer.h.6.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
545
- "transformer.h.6.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
546
- "transformer.h.6.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
547
- "transformer.h.7.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
548
- "transformer.h.7.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
549
- "transformer.h.7.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
550
- "transformer.h.7.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
551
- "transformer.h.7.ln_1.bias": "pytorch_model-00001-of-00002.bin",
552
- "transformer.h.7.ln_1.weight": "pytorch_model-00001-of-00002.bin",
553
- "transformer.h.7.ln_2.bias": "pytorch_model-00001-of-00002.bin",
554
- "transformer.h.7.ln_2.weight": "pytorch_model-00001-of-00002.bin",
555
- "transformer.h.7.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
556
- "transformer.h.7.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
557
- "transformer.h.7.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
558
- "transformer.h.7.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
559
- "transformer.h.8.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
560
- "transformer.h.8.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
561
- "transformer.h.8.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
562
- "transformer.h.8.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
563
- "transformer.h.8.ln_1.bias": "pytorch_model-00001-of-00002.bin",
564
- "transformer.h.8.ln_1.weight": "pytorch_model-00001-of-00002.bin",
565
- "transformer.h.8.ln_2.bias": "pytorch_model-00001-of-00002.bin",
566
- "transformer.h.8.ln_2.weight": "pytorch_model-00001-of-00002.bin",
567
- "transformer.h.8.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
568
- "transformer.h.8.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
569
- "transformer.h.8.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
570
- "transformer.h.8.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
571
- "transformer.h.9.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
572
- "transformer.h.9.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
573
- "transformer.h.9.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
574
- "transformer.h.9.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
575
- "transformer.h.9.ln_1.bias": "pytorch_model-00001-of-00002.bin",
576
- "transformer.h.9.ln_1.weight": "pytorch_model-00001-of-00002.bin",
577
- "transformer.h.9.ln_2.bias": "pytorch_model-00001-of-00002.bin",
578
- "transformer.h.9.ln_2.weight": "pytorch_model-00001-of-00002.bin",
579
- "transformer.h.9.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
580
- "transformer.h.9.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
581
- "transformer.h.9.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
582
- "transformer.h.9.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
583
- "transformer.ln_f.bias": "pytorch_model-00002-of-00002.bin",
584
- "transformer.ln_f.weight": "pytorch_model-00002-of-00002.bin",
585
- "transformer.wpe.weight": "pytorch_model-00001-of-00002.bin",
586
- "transformer.wte.weight": "pytorch_model-00001-of-00002.bin"
587
- }
588
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
gpt2-xl-pt/checkpoint-240000/rng_state_0.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:b1cca32baa7e615c81955526add607d3350487547493ad998e7c457edcd04dc6
3
- size 15024
 
 
 
 
gpt2-xl-pt/checkpoint-240000/rng_state_1.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:22167c6a52d2a9dbc95dcaa72535707e53b9b47990ff498db42a4f0bd62e542d
3
- size 15024
 
 
 
 
gpt2-xl-pt/checkpoint-240000/rng_state_2.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:5f2cf71deca2565168dca5e5019978b7cf0f9776b2c7a63ae230aa586b6c3593
3
- size 15024
 
 
 
 
gpt2-xl-pt/checkpoint-240000/rng_state_3.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:d1b2f83cdda2863192a44ae53e8a1c345df967a3718810a8e522b038babbf1c9
3
- size 15024
 
 
 
 
gpt2-xl-pt/checkpoint-240000/scheduler.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:125e71a4d2f4439d4912051c36abe8fcb76a0edb9d5fefe8edbadf2cca30613e
3
- size 1064
 
 
 
 
gpt2-xl-pt/checkpoint-240000/special_tokens_map.json DELETED
@@ -1,8 +0,0 @@
1
- {
2
- "bos_token": "<|endoftext|>",
3
- "eos_token": "<|endoftext|>",
4
- "mask_token": "------------",
5
- "pad_token": "<|endoftext|>",
6
- "sep_token": "======",
7
- "unk_token": "<|endoftext|>"
8
- }
 
 
 
 
 
 
 
 
 
gpt2-xl-pt/checkpoint-240000/tokenizer.json DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:1fe93b6152957cf9cfd6d89002467f789ce8b3f3e000b3a2edf27c808ddd0b9e
3
- size 3557680
 
 
 
 
gpt2-xl-pt/checkpoint-240000/tokenizer_config.json DELETED
@@ -1,26 +0,0 @@
1
- {
2
- "add_prefix_space": false,
3
- "added_tokens_decoder": {
4
- "50256": {
5
- "content": "<|endoftext|>",
6
- "lstrip": false,
7
- "normalized": true,
8
- "rstrip": false,
9
- "single_word": false,
10
- "special": true
11
- }
12
- },
13
- "bos_token": "<|endoftext|>",
14
- "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ system_message }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ content }}{% elif message['role'] == 'assistant' %}{{ content }}{% endif %}{% endfor %}",
15
- "clean_up_tokenization_spaces": false,
16
- "eos_token": "<|endoftext|>",
17
- "extra_special_tokens": {},
18
- "mask_token": "------------",
19
- "model_max_length": 1024,
20
- "pad_token": "<|endoftext|>",
21
- "padding_side": "right",
22
- "sep_token": "======",
23
- "split_special_tokens": false,
24
- "tokenizer_class": "GPT2Tokenizer",
25
- "unk_token": "<|endoftext|>"
26
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
gpt2-xl-pt/checkpoint-240000/trainer_state.json DELETED
The diff for this file is too large to render. See raw diff
 
gpt2-xl-pt/checkpoint-240000/training_args.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:e7d391756dd1f30115e58d744bf5706a5885cd4242b9ada8b6479c16bd95ed9e
3
- size 5560
 
 
 
 
gpt2-xl-pt/checkpoint-240000/vocab.json DELETED
The diff for this file is too large to render. See raw diff
 
gpt2-xl-pt/trainer_log.jsonl CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:deddfd71b0adeecc16a11c31ebc9a19f63b094b8a5b0d9fabfa7399c5b6aa0c7
3
- size 8130403
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8845b4e426ea3cc6f4f2914f3616d7466689ac1f7559846c2bf6a1eb0cc47c63
3
+ size 220