Hugging Face's logo

Clemylia
/
petit-test

Text Generation
Transformers
Safetensors
gpt2
text-generation-inference
Model card Files
xet
 Community
Clemylia commited on
Commit
6385810
·
verified ·
1 Parent(s): c7c54dc

Ajout du tokenizer associé au modèle final

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +9 -0
  2. tokenizer.json +103 -0
  3. tokenizer_config.json +49 -0
special_tokens_map.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "pad_token": {
3
+ "content": "[PAD]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ }
9
+ }
tokenizer.json ADDED
@@ -0,0 +1,103 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": null,
4
+ "padding": null,
5
+ "added_tokens": [
6
+ {
7
+ "id": 0,
8
+ "content": "[UNK]",
9
+ "single_word": false,
10
+ "lstrip": false,
11
+ "rstrip": false,
12
+ "normalized": false,
13
+ "special": true
14
+ },
15
+ {
16
+ "id": 1,
17
+ "content": "[CLS]",
18
+ "single_word": false,
19
+ "lstrip": false,
20
+ "rstrip": false,
21
+ "normalized": false,
22
+ "special": true
23
+ },
24
+ {
25
+ "id": 2,
26
+ "content": "[SEP]",
27
+ "single_word": false,
28
+ "lstrip": false,
29
+ "rstrip": false,
30
+ "normalized": false,
31
+ "special": true
32
+ },
33
+ {
34
+ "id": 3,
35
+ "content": "[PAD]",
36
+ "single_word": false,
37
+ "lstrip": false,
38
+ "rstrip": false,
39
+ "normalized": false,
40
+ "special": true
41
+ },
42
+ {
43
+ "id": 4,
44
+ "content": "[MASK]",
45
+ "single_word": false,
46
+ "lstrip": false,
47
+ "rstrip": false,
48
+ "normalized": false,
49
+ "special": true
50
+ }
51
+ ],
52
+ "normalizer": null,
53
+ "pre_tokenizer": {
54
+ "type": "Whitespace"
55
+ },
56
+ "post_processor": null,
57
+ "decoder": null,
58
+ "model": {
59
+ "type": "BPE",
60
+ "dropout": null,
61
+ "unk_token": "[UNK]",
62
+ "continuing_subword_prefix": null,
63
+ "end_of_word_suffix": null,
64
+ "fuse_unk": false,
65
+ "byte_fallback": false,
66
+ "ignore_merges": false,
67
+ "vocab": {
68
+ "[UNK]": 0,
69
+ "[CLS]": 1,
70
+ "[SEP]": 2,
71
+ "[PAD]": 3,
72
+ "[MASK]": 4,
73
+ ",": 5,
74
+ ".": 6,
75
+ "C": 7,
76
+ "G": 8,
77
+ "J": 9,
78
+ "a": 10,
79
+ "c": 11,
80
+ "d": 12,
81
+ "e": 13,
82
+ "f": 14,
83
+ "g": 15,
84
+ "h": 16,
85
+ "i": 17,
86
+ "l": 18,
87
+ "m": 19,
88
+ "n": 20,
89
+ "o": 21,
90
+ "p": 22,
91
+ "r": 23,
92
+ "s": 24,
93
+ "t": 25,
94
+ "u": 26,
95
+ "x": 27,
96
+ "y": 28,
97
+ "è": 29,
98
+ "é": 30,
99
+ "ô": 31
100
+ },
101
+ "merges": []
102
+ }
103
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[UNK]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "[CLS]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[SEP]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[PAD]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": false,
45
+ "extra_special_tokens": {},
46
+ "model_max_length": 1000000000000000019884624838656,
47
+ "pad_token": "[PAD]",
48
+ "tokenizer_class": "PreTrainedTokenizerFast"
49
+ }