Hugging Face's logo

JLsquare
/
chall-dataset-contamination

Text Generation
Transformers
PyTorch
French
gpt2
text-generation-inference
Model card Files Community
1
JLsquare commited on
Commit
16c3fbd
·
1 Parent(s): 4a50a9f

Upload model

Browse files
Files changed (9) hide show
  1. added_tokens.json +22 -0
  2. config.json +39 -0
  3. generation_config.json +6 -0
  4. merges.txt +0 -0
  5. pytorch_model.bin +3 -0
  6. special_tokens_map.json +6 -0
  7. tokenizer_config.json +178 -0
  8. training_args.bin +3 -0
  9. vocab.json +0 -0
added_tokens.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "0": 16,
3
+ "1": 17,
4
+ "3": 19,
5
+ "4": 20,
6
+ "<|endoftext|>": 0,
7
+ "D": 36,
8
+ "F": 38,
9
+ "I": 41,
10
+ "K": 43,
11
+ "L": 44,
12
+ "M": 45,
13
+ "N": 46,
14
+ "R": 50,
15
+ "T": 52,
16
+ "U": 50000,
17
+ "X": 50002,
18
+ "Y": 50001,
19
+ "_": 59,
20
+ "{": 87,
21
+ "}": 89
22
+ }
config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "ClassCat/gpt2-base-french",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPT2LMHeadModel"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 0,
9
+ "embd_pdrop": 0.1,
10
+ "eos_token_id": 0,
11
+ "initializer_range": 0.02,
12
+ "layer_norm_epsilon": 1e-05,
13
+ "model_type": "gpt2",
14
+ "n_ctx": 1024,
15
+ "n_embd": 768,
16
+ "n_head": 12,
17
+ "n_inner": null,
18
+ "n_layer": 12,
19
+ "n_positions": 1024,
20
+ "reorder_and_upcast_attn": false,
21
+ "resid_pdrop": 0.1,
22
+ "scale_attn_by_inverse_layer_idx": false,
23
+ "scale_attn_weights": true,
24
+ "summary_activation": null,
25
+ "summary_first_dropout": 0.1,
26
+ "summary_proj_to_labels": true,
27
+ "summary_type": "cls_index",
28
+ "summary_use_proj": true,
29
+ "task_specific_params": {
30
+ "text-generation": {
31
+ "do_sample": true,
32
+ "max_length": 50
33
+ }
34
+ },
35
+ "torch_dtype": "float32",
36
+ "transformers_version": "4.34.0",
37
+ "use_cache": true,
38
+ "vocab_size": 50003
39
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 0,
5
+ "transformers_version": "4.34.0"
6
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:978818a737148d145f90807bbf07ef269d4b45e73f6df9492a38b691d1bfd61b
3
+ size 497027418
special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "pad_token": "<|endoftext|>",
5
+ "unk_token": "<|endoftext|>"
6
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,178 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": false
12
+ },
13
+ "16": {
14
+ "content": "0",
15
+ "lstrip": true,
16
+ "normalized": true,
17
+ "rstrip": true,
18
+ "single_word": false,
19
+ "special": false
20
+ },
21
+ "17": {
22
+ "content": "1",
23
+ "lstrip": true,
24
+ "normalized": true,
25
+ "rstrip": true,
26
+ "single_word": false,
27
+ "special": false
28
+ },
29
+ "19": {
30
+ "content": "3",
31
+ "lstrip": true,
32
+ "normalized": true,
33
+ "rstrip": true,
34
+ "single_word": false,
35
+ "special": false
36
+ },
37
+ "20": {
38
+ "content": "4",
39
+ "lstrip": true,
40
+ "normalized": true,
41
+ "rstrip": true,
42
+ "single_word": false,
43
+ "special": false
44
+ },
45
+ "36": {
46
+ "content": "D",
47
+ "lstrip": true,
48
+ "normalized": true,
49
+ "rstrip": true,
50
+ "single_word": false,
51
+ "special": false
52
+ },
53
+ "38": {
54
+ "content": "F",
55
+ "lstrip": true,
56
+ "normalized": true,
57
+ "rstrip": true,
58
+ "single_word": false,
59
+ "special": false
60
+ },
61
+ "41": {
62
+ "content": "I",
63
+ "lstrip": true,
64
+ "normalized": true,
65
+ "rstrip": true,
66
+ "single_word": false,
67
+ "special": false
68
+ },
69
+ "43": {
70
+ "content": "K",
71
+ "lstrip": true,
72
+ "normalized": true,
73
+ "rstrip": true,
74
+ "single_word": false,
75
+ "special": false
76
+ },
77
+ "44": {
78
+ "content": "L",
79
+ "lstrip": true,
80
+ "normalized": true,
81
+ "rstrip": true,
82
+ "single_word": false,
83
+ "special": false
84
+ },
85
+ "45": {
86
+ "content": "M",
87
+ "lstrip": true,
88
+ "normalized": true,
89
+ "rstrip": true,
90
+ "single_word": false,
91
+ "special": false
92
+ },
93
+ "46": {
94
+ "content": "N",
95
+ "lstrip": true,
96
+ "normalized": true,
97
+ "rstrip": true,
98
+ "single_word": false,
99
+ "special": false
100
+ },
101
+ "50": {
102
+ "content": "R",
103
+ "lstrip": true,
104
+ "normalized": true,
105
+ "rstrip": true,
106
+ "single_word": false,
107
+ "special": false
108
+ },
109
+ "52": {
110
+ "content": "T",
111
+ "lstrip": true,
112
+ "normalized": true,
113
+ "rstrip": true,
114
+ "single_word": false,
115
+ "special": false
116
+ },
117
+ "59": {
118
+ "content": "_",
119
+ "lstrip": true,
120
+ "normalized": true,
121
+ "rstrip": true,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "87": {
126
+ "content": "{",
127
+ "lstrip": true,
128
+ "normalized": true,
129
+ "rstrip": true,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "89": {
134
+ "content": "}",
135
+ "lstrip": true,
136
+ "normalized": true,
137
+ "rstrip": true,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "50000": {
142
+ "content": "U",
143
+ "lstrip": true,
144
+ "normalized": true,
145
+ "rstrip": true,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "50001": {
150
+ "content": "Y",
151
+ "lstrip": true,
152
+ "normalized": true,
153
+ "rstrip": true,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "50002": {
158
+ "content": "X",
159
+ "lstrip": true,
160
+ "normalized": true,
161
+ "rstrip": true,
162
+ "single_word": false,
163
+ "special": false
164
+ }
165
+ },
166
+ "additional_special_tokens": [],
167
+ "bos_token": "<|endoftext|>",
168
+ "clean_up_tokenization_spaces": true,
169
+ "eos_token": "<|endoftext|>",
170
+ "errors": "replace",
171
+ "keep_accents": true,
172
+ "max_len": 50,
173
+ "model_max_length": 50,
174
+ "pad_token": "<|endoftext|>",
175
+ "tokenizer_class": "GPT2Tokenizer",
176
+ "tokenizer_file": "/home/jl/.cache/huggingface/hub/models--ClassCat--gpt2-base-french/snapshots/902ec822995ce12f979d0a5277ee9c2a1b610df1/tokenizer.json",
177
+ "unk_token": "<|endoftext|>"
178
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7604d85e7b1fa3ac67ae31a254bbad12f9ae05dd1c9b25a9bbbdc1ab2e08052
3
+ size 4408
vocab.json ADDED
The diff for this file is too large to render. See raw diff