Hugging Face's logo

ebony59
/
gptj-edit-100k

Text Generation
Transformers
PyTorch
gptj
Inference Endpoints
Model card Files Community
root commited on
Commit
3fd10a7
•
1 Parent(s): 3b02651

initial model upload

Browse files
Files changed (18) hide show
  1. added_tokens.json +145 -0
  2. config.json +42 -0
  3. generation_config.json +6 -0
  4. latest +1 -0
  5. merges.txt +0 -0
  6. pytorch_model-00001-of-00002.bin +3 -0
  7. pytorch_model-00002-of-00002.bin +3 -0
  8. pytorch_model.bin.index.json +292 -0
  9. rng_state_0.pth +3 -0
  10. rng_state_1.pth +3 -0
  11. rng_state_2.pth +3 -0
  12. rng_state_3.pth +3 -0
  13. special_tokens_map.json +24 -0
  14. tokenizer.json +0 -0
  15. tokenizer_config.json +35 -0
  16. trainer_state.json +0 -0
  17. training_args.bin +3 -0
  18. vocab.json +0 -0
added_tokens.json ADDED
@@ -0,0 +1,145 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<|extratoken_100|>": 50356,
3
+ "<|extratoken_101|>": 50357,
4
+ "<|extratoken_102|>": 50358,
5
+ "<|extratoken_103|>": 50359,
6
+ "<|extratoken_104|>": 50360,
7
+ "<|extratoken_105|>": 50361,
8
+ "<|extratoken_106|>": 50362,
9
+ "<|extratoken_107|>": 50363,
10
+ "<|extratoken_108|>": 50364,
11
+ "<|extratoken_109|>": 50365,
12
+ "<|extratoken_10|>": 50266,
13
+ "<|extratoken_110|>": 50366,
14
+ "<|extratoken_111|>": 50367,
15
+ "<|extratoken_112|>": 50368,
16
+ "<|extratoken_113|>": 50369,
17
+ "<|extratoken_114|>": 50370,
18
+ "<|extratoken_115|>": 50371,
19
+ "<|extratoken_116|>": 50372,
20
+ "<|extratoken_117|>": 50373,
21
+ "<|extratoken_118|>": 50374,
22
+ "<|extratoken_119|>": 50375,
23
+ "<|extratoken_11|>": 50267,
24
+ "<|extratoken_120|>": 50376,
25
+ "<|extratoken_121|>": 50377,
26
+ "<|extratoken_122|>": 50378,
27
+ "<|extratoken_123|>": 50379,
28
+ "<|extratoken_124|>": 50380,
29
+ "<|extratoken_125|>": 50381,
30
+ "<|extratoken_126|>": 50382,
31
+ "<|extratoken_127|>": 50383,
32
+ "<|extratoken_128|>": 50384,
33
+ "<|extratoken_129|>": 50385,
34
+ "<|extratoken_12|>": 50268,
35
+ "<|extratoken_130|>": 50386,
36
+ "<|extratoken_131|>": 50387,
37
+ "<|extratoken_132|>": 50388,
38
+ "<|extratoken_133|>": 50389,
39
+ "<|extratoken_134|>": 50390,
40
+ "<|extratoken_135|>": 50391,
41
+ "<|extratoken_136|>": 50392,
42
+ "<|extratoken_137|>": 50393,
43
+ "<|extratoken_138|>": 50394,
44
+ "<|extratoken_139|>": 50395,
45
+ "<|extratoken_13|>": 50269,
46
+ "<|extratoken_140|>": 50396,
47
+ "<|extratoken_141|>": 50397,
48
+ "<|extratoken_142|>": 50398,
49
+ "<|extratoken_143|>": 50399,
50
+ "<|extratoken_14|>": 50270,
51
+ "<|extratoken_15|>": 50271,
52
+ "<|extratoken_16|>": 50272,
53
+ "<|extratoken_17|>": 50273,
54
+ "<|extratoken_18|>": 50274,
55
+ "<|extratoken_19|>": 50275,
56
+ "<|extratoken_1|>": 50257,
57
+ "<|extratoken_20|>": 50276,
58
+ "<|extratoken_21|>": 50277,
59
+ "<|extratoken_22|>": 50278,
60
+ "<|extratoken_23|>": 50279,
61
+ "<|extratoken_24|>": 50280,
62
+ "<|extratoken_25|>": 50281,
63
+ "<|extratoken_26|>": 50282,
64
+ "<|extratoken_27|>": 50283,
65
+ "<|extratoken_28|>": 50284,
66
+ "<|extratoken_29|>": 50285,
67
+ "<|extratoken_2|>": 50258,
68
+ "<|extratoken_30|>": 50286,
69
+ "<|extratoken_31|>": 50287,
70
+ "<|extratoken_32|>": 50288,
71
+ "<|extratoken_33|>": 50289,
72
+ "<|extratoken_34|>": 50290,
73
+ "<|extratoken_35|>": 50291,
74
+ "<|extratoken_36|>": 50292,
75
+ "<|extratoken_37|>": 50293,
76
+ "<|extratoken_38|>": 50294,
77
+ "<|extratoken_39|>": 50295,
78
+ "<|extratoken_3|>": 50259,
79
+ "<|extratoken_40|>": 50296,
80
+ "<|extratoken_41|>": 50297,
81
+ "<|extratoken_42|>": 50298,
82
+ "<|extratoken_43|>": 50299,
83
+ "<|extratoken_44|>": 50300,
84
+ "<|extratoken_45|>": 50301,
85
+ "<|extratoken_46|>": 50302,
86
+ "<|extratoken_47|>": 50303,
87
+ "<|extratoken_48|>": 50304,
88
+ "<|extratoken_49|>": 50305,
89
+ "<|extratoken_4|>": 50260,
90
+ "<|extratoken_50|>": 50306,
91
+ "<|extratoken_51|>": 50307,
92
+ "<|extratoken_52|>": 50308,
93
+ "<|extratoken_53|>": 50309,
94
+ "<|extratoken_54|>": 50310,
95
+ "<|extratoken_55|>": 50311,
96
+ "<|extratoken_56|>": 50312,
97
+ "<|extratoken_57|>": 50313,
98
+ "<|extratoken_58|>": 50314,
99
+ "<|extratoken_59|>": 50315,
100
+ "<|extratoken_5|>": 50261,
101
+ "<|extratoken_60|>": 50316,
102
+ "<|extratoken_61|>": 50317,
103
+ "<|extratoken_62|>": 50318,
104
+ "<|extratoken_63|>": 50319,
105
+ "<|extratoken_64|>": 50320,
106
+ "<|extratoken_65|>": 50321,
107
+ "<|extratoken_66|>": 50322,
108
+ "<|extratoken_67|>": 50323,
109
+ "<|extratoken_68|>": 50324,
110
+ "<|extratoken_69|>": 50325,
111
+ "<|extratoken_6|>": 50262,
112
+ "<|extratoken_70|>": 50326,
113
+ "<|extratoken_71|>": 50327,
114
+ "<|extratoken_72|>": 50328,
115
+ "<|extratoken_73|>": 50329,
116
+ "<|extratoken_74|>": 50330,
117
+ "<|extratoken_75|>": 50331,
118
+ "<|extratoken_76|>": 50332,
119
+ "<|extratoken_77|>": 50333,
120
+ "<|extratoken_78|>": 50334,
121
+ "<|extratoken_79|>": 50335,
122
+ "<|extratoken_7|>": 50263,
123
+ "<|extratoken_80|>": 50336,
124
+ "<|extratoken_81|>": 50337,
125
+ "<|extratoken_82|>": 50338,
126
+ "<|extratoken_83|>": 50339,
127
+ "<|extratoken_84|>": 50340,
128
+ "<|extratoken_85|>": 50341,
129
+ "<|extratoken_86|>": 50342,
130
+ "<|extratoken_87|>": 50343,
131
+ "<|extratoken_88|>": 50344,
132
+ "<|extratoken_89|>": 50345,
133
+ "<|extratoken_8|>": 50264,
134
+ "<|extratoken_90|>": 50346,
135
+ "<|extratoken_91|>": 50347,
136
+ "<|extratoken_92|>": 50348,
137
+ "<|extratoken_93|>": 50349,
138
+ "<|extratoken_94|>": 50350,
139
+ "<|extratoken_95|>": 50351,
140
+ "<|extratoken_96|>": 50352,
141
+ "<|extratoken_97|>": 50353,
142
+ "<|extratoken_98|>": 50354,
143
+ "<|extratoken_99|>": 50355,
144
+ "<|extratoken_9|>": 50265
145
+ }
config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "EleutherAI/gpt-j-6b",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPTJForCausalLM"
6
+ ],
7
+ "attn_pdrop": 0.0,
8
+ "bos_token_id": 50256,
9
+ "embd_pdrop": 0.0,
10
+ "eos_token_id": 50256,
11
+ "gradient_checkpointing": false,
12
+ "initializer_range": 0.02,
13
+ "layer_norm_epsilon": 1e-05,
14
+ "model_type": "gptj",
15
+ "n_embd": 4096,
16
+ "n_head": 16,
17
+ "n_inner": null,
18
+ "n_layer": 28,
19
+ "n_positions": 2048,
20
+ "resid_pdrop": 0.0,
21
+ "rotary": true,
22
+ "rotary_dim": 64,
23
+ "scale_attn_weights": true,
24
+ "summary_activation": null,
25
+ "summary_first_dropout": 0.1,
26
+ "summary_proj_to_labels": true,
27
+ "summary_type": "cls_index",
28
+ "summary_use_proj": true,
29
+ "task_specific_params": {
30
+ "text-generation": {
31
+ "do_sample": true,
32
+ "max_length": 50,
33
+ "temperature": 1.0
34
+ }
35
+ },
36
+ "tie_word_embeddings": false,
37
+ "tokenizer_class": "GPT2Tokenizer",
38
+ "torch_dtype": "bfloat16",
39
+ "transformers_version": "4.31.0",
40
+ "use_cache": true,
41
+ "vocab_size": 50400
42
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "eos_token_id": 50256,
5
+ "transformers_version": "4.31.0"
6
+ }
latest ADDED
@@ -0,0 +1 @@
 
 
1
+ global_step6187
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model-00001-of-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ac5044740fd7c296103eb65c6ab9eb8343c2af30c222d60f591675fb6556666
3
+ size 9943784244
pytorch_model-00002-of-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2dc530b41f9cc803f7f6b9cd03b57a28a215dfd0a7592e599f1bb15fb5c84ac
3
+ size 2158077003
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,292 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 12101765568
4
+ },
5
+ "weight_map": {
6
+ "lm_head.bias": "pytorch_model-00002-of-00002.bin",
7
+ "lm_head.weight": "pytorch_model-00002-of-00002.bin",
8
+ "transformer.h.0.attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
9
+ "transformer.h.0.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
10
+ "transformer.h.0.attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
11
+ "transformer.h.0.attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
12
+ "transformer.h.0.ln_1.bias": "pytorch_model-00001-of-00002.bin",
13
+ "transformer.h.0.ln_1.weight": "pytorch_model-00001-of-00002.bin",
14
+ "transformer.h.0.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
15
+ "transformer.h.0.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
16
+ "transformer.h.0.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
17
+ "transformer.h.0.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
18
+ "transformer.h.1.attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
19
+ "transformer.h.1.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
20
+ "transformer.h.1.attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
21
+ "transformer.h.1.attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
22
+ "transformer.h.1.ln_1.bias": "pytorch_model-00001-of-00002.bin",
23
+ "transformer.h.1.ln_1.weight": "pytorch_model-00001-of-00002.bin",
24
+ "transformer.h.1.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
25
+ "transformer.h.1.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
26
+ "transformer.h.1.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
27
+ "transformer.h.1.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
28
+ "transformer.h.10.attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
29
+ "transformer.h.10.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
30
+ "transformer.h.10.attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
31
+ "transformer.h.10.attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
32
+ "transformer.h.10.ln_1.bias": "pytorch_model-00001-of-00002.bin",
33
+ "transformer.h.10.ln_1.weight": "pytorch_model-00001-of-00002.bin",
34
+ "transformer.h.10.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
35
+ "transformer.h.10.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
36
+ "transformer.h.10.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
37
+ "transformer.h.10.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
38
+ "transformer.h.11.attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
39
+ "transformer.h.11.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
40
+ "transformer.h.11.attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
41
+ "transformer.h.11.attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
42
+ "transformer.h.11.ln_1.bias": "pytorch_model-00001-of-00002.bin",
43
+ "transformer.h.11.ln_1.weight": "pytorch_model-00001-of-00002.bin",
44
+ "transformer.h.11.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
45
+ "transformer.h.11.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
46
+ "transformer.h.11.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
47
+ "transformer.h.11.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
48
+ "transformer.h.12.attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
49
+ "transformer.h.12.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
50
+ "transformer.h.12.attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
51
+ "transformer.h.12.attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
52
+ "transformer.h.12.ln_1.bias": "pytorch_model-00001-of-00002.bin",
53
+ "transformer.h.12.ln_1.weight": "pytorch_model-00001-of-00002.bin",
54
+ "transformer.h.12.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
55
+ "transformer.h.12.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
56
+ "transformer.h.12.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
57
+ "transformer.h.12.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
58
+ "transformer.h.13.attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
59
+ "transformer.h.13.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
60
+ "transformer.h.13.attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
61
+ "transformer.h.13.attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
62
+ "transformer.h.13.ln_1.bias": "pytorch_model-00001-of-00002.bin",
63
+ "transformer.h.13.ln_1.weight": "pytorch_model-00001-of-00002.bin",
64
+ "transformer.h.13.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
65
+ "transformer.h.13.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
66
+ "transformer.h.13.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
67
+ "transformer.h.13.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
68
+ "transformer.h.14.attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
69
+ "transformer.h.14.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
70
+ "transformer.h.14.attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
71
+ "transformer.h.14.attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
72
+ "transformer.h.14.ln_1.bias": "pytorch_model-00001-of-00002.bin",
73
+ "transformer.h.14.ln_1.weight": "pytorch_model-00001-of-00002.bin",
74
+ "transformer.h.14.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
75
+ "transformer.h.14.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
76
+ "transformer.h.14.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
77
+ "transformer.h.14.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
78
+ "transformer.h.15.attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
79
+ "transformer.h.15.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
80
+ "transformer.h.15.attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
81
+ "transformer.h.15.attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
82
+ "transformer.h.15.ln_1.bias": "pytorch_model-00001-of-00002.bin",
83
+ "transformer.h.15.ln_1.weight": "pytorch_model-00001-of-00002.bin",
84
+ "transformer.h.15.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
85
+ "transformer.h.15.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
86
+ "transformer.h.15.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
87
+ "transformer.h.15.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
88
+ "transformer.h.16.attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
89
+ "transformer.h.16.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
90
+ "transformer.h.16.attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
91
+ "transformer.h.16.attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
92
+ "transformer.h.16.ln_1.bias": "pytorch_model-00001-of-00002.bin",
93
+ "transformer.h.16.ln_1.weight": "pytorch_model-00001-of-00002.bin",
94
+ "transformer.h.16.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
95
+ "transformer.h.16.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
96
+ "transformer.h.16.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
97
+ "transformer.h.16.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
98
+ "transformer.h.17.attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
99
+ "transformer.h.17.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
100
+ "transformer.h.17.attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
101
+ "transformer.h.17.attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
102
+ "transformer.h.17.ln_1.bias": "pytorch_model-00001-of-00002.bin",
103
+ "transformer.h.17.ln_1.weight": "pytorch_model-00001-of-00002.bin",
104
+ "transformer.h.17.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
105
+ "transformer.h.17.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
106
+ "transformer.h.17.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
107
+ "transformer.h.17.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
108
+ "transformer.h.18.attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
109
+ "transformer.h.18.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
110
+ "transformer.h.18.attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
111
+ "transformer.h.18.attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
112
+ "transformer.h.18.ln_1.bias": "pytorch_model-00001-of-00002.bin",
113
+ "transformer.h.18.ln_1.weight": "pytorch_model-00001-of-00002.bin",
114
+ "transformer.h.18.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
115
+ "transformer.h.18.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
116
+ "transformer.h.18.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
117
+ "transformer.h.18.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
118
+ "transformer.h.19.attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
119
+ "transformer.h.19.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
120
+ "transformer.h.19.attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
121
+ "transformer.h.19.attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
122
+ "transformer.h.19.ln_1.bias": "pytorch_model-00001-of-00002.bin",
123
+ "transformer.h.19.ln_1.weight": "pytorch_model-00001-of-00002.bin",
124
+ "transformer.h.19.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
125
+ "transformer.h.19.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
126
+ "transformer.h.19.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
127
+ "transformer.h.19.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
128
+ "transformer.h.2.attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
129
+ "transformer.h.2.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
130
+ "transformer.h.2.attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
131
+ "transformer.h.2.attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
132
+ "transformer.h.2.ln_1.bias": "pytorch_model-00001-of-00002.bin",
133
+ "transformer.h.2.ln_1.weight": "pytorch_model-00001-of-00002.bin",
134
+ "transformer.h.2.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
135
+ "transformer.h.2.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
136
+ "transformer.h.2.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
137
+ "transformer.h.2.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
138
+ "transformer.h.20.attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
139
+ "transformer.h.20.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
140
+ "transformer.h.20.attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
141
+ "transformer.h.20.attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
142
+ "transformer.h.20.ln_1.bias": "pytorch_model-00001-of-00002.bin",
143
+ "transformer.h.20.ln_1.weight": "pytorch_model-00001-of-00002.bin",
144
+ "transformer.h.20.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
145
+ "transformer.h.20.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
146
+ "transformer.h.20.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
147
+ "transformer.h.20.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
148
+ "transformer.h.21.attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
149
+ "transformer.h.21.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
150
+ "transformer.h.21.attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
151
+ "transformer.h.21.attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
152
+ "transformer.h.21.ln_1.bias": "pytorch_model-00001-of-00002.bin",
153
+ "transformer.h.21.ln_1.weight": "pytorch_model-00001-of-00002.bin",
154
+ "transformer.h.21.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
155
+ "transformer.h.21.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
156
+ "transformer.h.21.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
157
+ "transformer.h.21.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
158
+ "transformer.h.22.attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
159
+ "transformer.h.22.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
160
+ "transformer.h.22.attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
161
+ "transformer.h.22.attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
162
+ "transformer.h.22.ln_1.bias": "pytorch_model-00001-of-00002.bin",
163
+ "transformer.h.22.ln_1.weight": "pytorch_model-00001-of-00002.bin",
164
+ "transformer.h.22.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
165
+ "transformer.h.22.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
166
+ "transformer.h.22.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
167
+ "transformer.h.22.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
168
+ "transformer.h.23.attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
169
+ "transformer.h.23.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
170
+ "transformer.h.23.attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
171
+ "transformer.h.23.attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
172
+ "transformer.h.23.ln_1.bias": "pytorch_model-00001-of-00002.bin",
173
+ "transformer.h.23.ln_1.weight": "pytorch_model-00001-of-00002.bin",
174
+ "transformer.h.23.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
175
+ "transformer.h.23.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
176
+ "transformer.h.23.mlp.fc_out.bias": "pytorch_model-00002-of-00002.bin",
177
+ "transformer.h.23.mlp.fc_out.weight": "pytorch_model-00002-of-00002.bin",
178
+ "transformer.h.24.attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
179
+ "transformer.h.24.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
180
+ "transformer.h.24.attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
181
+ "transformer.h.24.attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
182
+ "transformer.h.24.ln_1.bias": "pytorch_model-00002-of-00002.bin",
183
+ "transformer.h.24.ln_1.weight": "pytorch_model-00002-of-00002.bin",
184
+ "transformer.h.24.mlp.fc_in.bias": "pytorch_model-00002-of-00002.bin",
185
+ "transformer.h.24.mlp.fc_in.weight": "pytorch_model-00002-of-00002.bin",
186
+ "transformer.h.24.mlp.fc_out.bias": "pytorch_model-00002-of-00002.bin",
187
+ "transformer.h.24.mlp.fc_out.weight": "pytorch_model-00002-of-00002.bin",
188
+ "transformer.h.25.attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
189
+ "transformer.h.25.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
190
+ "transformer.h.25.attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
191
+ "transformer.h.25.attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
192
+ "transformer.h.25.ln_1.bias": "pytorch_model-00002-of-00002.bin",
193
+ "transformer.h.25.ln_1.weight": "pytorch_model-00002-of-00002.bin",
194
+ "transformer.h.25.mlp.fc_in.bias": "pytorch_model-00002-of-00002.bin",
195
+ "transformer.h.25.mlp.fc_in.weight": "pytorch_model-00002-of-00002.bin",
196
+ "transformer.h.25.mlp.fc_out.bias": "pytorch_model-00002-of-00002.bin",
197
+ "transformer.h.25.mlp.fc_out.weight": "pytorch_model-00002-of-00002.bin",
198
+ "transformer.h.26.attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
199
+ "transformer.h.26.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
200
+ "transformer.h.26.attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
201
+ "transformer.h.26.attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
202
+ "transformer.h.26.ln_1.bias": "pytorch_model-00002-of-00002.bin",
203
+ "transformer.h.26.ln_1.weight": "pytorch_model-00002-of-00002.bin",
204
+ "transformer.h.26.mlp.fc_in.bias": "pytorch_model-00002-of-00002.bin",
205
+ "transformer.h.26.mlp.fc_in.weight": "pytorch_model-00002-of-00002.bin",
206
+ "transformer.h.26.mlp.fc_out.bias": "pytorch_model-00002-of-00002.bin",
207
+ "transformer.h.26.mlp.fc_out.weight": "pytorch_model-00002-of-00002.bin",
208
+ "transformer.h.27.attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
209
+ "transformer.h.27.attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
210
+ "transformer.h.27.attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
211
+ "transformer.h.27.attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
212
+ "transformer.h.27.ln_1.bias": "pytorch_model-00002-of-00002.bin",
213
+ "transformer.h.27.ln_1.weight": "pytorch_model-00002-of-00002.bin",
214
+ "transformer.h.27.mlp.fc_in.bias": "pytorch_model-00002-of-00002.bin",
215
+ "transformer.h.27.mlp.fc_in.weight": "pytorch_model-00002-of-00002.bin",
216
+ "transformer.h.27.mlp.fc_out.bias": "pytorch_model-00002-of-00002.bin",
217
+ "transformer.h.27.mlp.fc_out.weight": "pytorch_model-00002-of-00002.bin",
218
+ "transformer.h.3.attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
219
+ "transformer.h.3.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
220
+ "transformer.h.3.attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
221
+ "transformer.h.3.attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
222
+ "transformer.h.3.ln_1.bias": "pytorch_model-00001-of-00002.bin",
223
+ "transformer.h.3.ln_1.weight": "pytorch_model-00001-of-00002.bin",
224
+ "transformer.h.3.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
225
+ "transformer.h.3.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
226
+ "transformer.h.3.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
227
+ "transformer.h.3.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
228
+ "transformer.h.4.attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
229
+ "transformer.h.4.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
230
+ "transformer.h.4.attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
231
+ "transformer.h.4.attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
232
+ "transformer.h.4.ln_1.bias": "pytorch_model-00001-of-00002.bin",
233
+ "transformer.h.4.ln_1.weight": "pytorch_model-00001-of-00002.bin",
234
+ "transformer.h.4.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
235
+ "transformer.h.4.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
236
+ "transformer.h.4.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
237
+ "transformer.h.4.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
238
+ "transformer.h.5.attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
239
+ "transformer.h.5.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
240
+ "transformer.h.5.attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
241
+ "transformer.h.5.attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
242
+ "transformer.h.5.ln_1.bias": "pytorch_model-00001-of-00002.bin",
243
+ "transformer.h.5.ln_1.weight": "pytorch_model-00001-of-00002.bin",
244
+ "transformer.h.5.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
245
+ "transformer.h.5.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
246
+ "transformer.h.5.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
247
+ "transformer.h.5.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
248
+ "transformer.h.6.attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
249
+ "transformer.h.6.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
250
+ "transformer.h.6.attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
251
+ "transformer.h.6.attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
252
+ "transformer.h.6.ln_1.bias": "pytorch_model-00001-of-00002.bin",
253
+ "transformer.h.6.ln_1.weight": "pytorch_model-00001-of-00002.bin",
254
+ "transformer.h.6.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
255
+ "transformer.h.6.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
256
+ "transformer.h.6.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
257
+ "transformer.h.6.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
258
+ "transformer.h.7.attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
259
+ "transformer.h.7.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
260
+ "transformer.h.7.attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
261
+ "transformer.h.7.attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
262
+ "transformer.h.7.ln_1.bias": "pytorch_model-00001-of-00002.bin",
263
+ "transformer.h.7.ln_1.weight": "pytorch_model-00001-of-00002.bin",
264
+ "transformer.h.7.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
265
+ "transformer.h.7.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
266
+ "transformer.h.7.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
267
+ "transformer.h.7.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
268
+ "transformer.h.8.attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
269
+ "transformer.h.8.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
270
+ "transformer.h.8.attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
271
+ "transformer.h.8.attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
272
+ "transformer.h.8.ln_1.bias": "pytorch_model-00001-of-00002.bin",
273
+ "transformer.h.8.ln_1.weight": "pytorch_model-00001-of-00002.bin",
274
+ "transformer.h.8.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
275
+ "transformer.h.8.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
276
+ "transformer.h.8.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
277
+ "transformer.h.8.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
278
+ "transformer.h.9.attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
279
+ "transformer.h.9.attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
280
+ "transformer.h.9.attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
281
+ "transformer.h.9.attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
282
+ "transformer.h.9.ln_1.bias": "pytorch_model-00001-of-00002.bin",
283
+ "transformer.h.9.ln_1.weight": "pytorch_model-00001-of-00002.bin",
284
+ "transformer.h.9.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
285
+ "transformer.h.9.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
286
+ "transformer.h.9.mlp.fc_out.bias": "pytorch_model-00001-of-00002.bin",
287
+ "transformer.h.9.mlp.fc_out.weight": "pytorch_model-00001-of-00002.bin",
288
+ "transformer.ln_f.bias": "pytorch_model-00002-of-00002.bin",
289
+ "transformer.ln_f.weight": "pytorch_model-00002-of-00002.bin",
290
+ "transformer.wte.weight": "pytorch_model-00001-of-00002.bin"
291
+ }
292
+ }
rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:456715cd46b4078166e5066d28c038ec453e3e3b3d8406687046b01fc249028d
3
+ size 17527
rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5458461c70e553c676000c93b98d37b5d397c5884e1bf555c47c39697fcd4b8c
3
+ size 17527
rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3fe31c894147257d6a9e28a1943cd3ff2507b3b9f6252ae4e3c92924806d8f5e
3
+ size 17527
rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56bb37fdf3fec918dad0ce6723c80cd28356e0e91c173ccb71c03456e5316659
3
+ size 17527
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|endoftext|>",
17
+ "unk_token": {
18
+ "content": "<|endoftext|>",
19
+ "lstrip": false,
20
+ "normalized": true,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "bos_token": {
5
+ "__type": "AddedToken",
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "clean_up_tokenization_spaces": true,
13
+ "eos_token": {
14
+ "__type": "AddedToken",
15
+ "content": "<|endoftext|>",
16
+ "lstrip": false,
17
+ "normalized": true,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "errors": "replace",
22
+ "model_max_length": 2048,
23
+ "pad_token": null,
24
+ "padding_side": "left",
25
+ "tokenizer_class": "GPT2Tokenizer",
26
+ "truncation_side": "left",
27
+ "unk_token": {
28
+ "__type": "AddedToken",
29
+ "content": "<|endoftext|>",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false
34
+ }
35
+ }
trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e412a27a9859d472a3014333bc99c432c4be0f898e9cee5f44845e0c4b38a1e
3
+ size 5499
vocab.json ADDED
The diff for this file is too large to render. See raw diff