Hugging Face's logo

ncardus
/
charTokenizerModel

Model card Files
xet
 Community
ncardus commited on
Commit
6290ae1
·
1 Parent(s): 393b225

Upload tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +7 -0
  2. tokenizer.json +147 -0
  3. tokenizer_config.json +10 -0
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
tokenizer.json ADDED
@@ -0,0 +1,147 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "[PAD]",
18
+ "single_word": false,
19
+ "lstrip": false,
20
+ "rstrip": false,
21
+ "normalized": false,
22
+ "special": true
23
+ },
24
+ {
25
+ "id": 2,
26
+ "content": "[CLS]",
27
+ "single_word": false,
28
+ "lstrip": false,
29
+ "rstrip": false,
30
+ "normalized": false,
31
+ "special": true
32
+ },
33
+ {
34
+ "id": 3,
35
+ "content": "[SEP]",
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": {
53
+ "type": "Sequence",
54
+ "normalizers": [
55
+ {
56
+ "type": "Lowercase"
57
+ },
58
+ {
59
+ "type": "NFKD"
60
+ }
61
+ ]
62
+ },
63
+ "pre_tokenizer": {
64
+ "type": "Sequence",
65
+ "pretokenizers": [
66
+ {
67
+ "type": "Whitespace"
68
+ },
69
+ {
70
+ "type": "Digits",
71
+ "individual_digits": false
72
+ }
73
+ ]
74
+ },
75
+ "post_processor": {
76
+ "type": "BertProcessing",
77
+ "sep": [
78
+ "[SEP]",
79
+ 0
80
+ ],
81
+ "cls": [
82
+ "[CLS]",
83
+ 1
84
+ ]
85
+ },
86
+ "decoder": null,
87
+ "model": {
88
+ "type": "BPE",
89
+ "dropout": null,
90
+ "unk_token": "[UNK]",
91
+ "continuing_subword_prefix": null,
92
+ "end_of_word_suffix": null,
93
+ "fuse_unk": false,
94
+ "byte_fallback": false,
95
+ "vocab": {
96
+ "[UNK]": 0,
97
+ "[PAD]": 1,
98
+ "[CLS]": 2,
99
+ "[SEP]": 3,
100
+ "[MASK]": 4,
101
+ "'": 5,
102
+ "(": 6,
103
+ ")": 7,
104
+ "-": 8,
105
+ ".": 9,
106
+ "0": 10,
107
+ "1": 11,
108
+ "2": 12,
109
+ "4": 13,
110
+ "5": 14,
111
+ "8": 15,
112
+ "[": 16,
113
+ "]": 17,
114
+ "_": 18,
115
+ "a": 19,
116
+ "b": 20,
117
+ "c": 21,
118
+ "d": 22,
119
+ "e": 23,
120
+ "f": 24,
121
+ "g": 25,
122
+ "h": 26,
123
+ "i": 27,
124
+ "j": 28,
125
+ "k": 29,
126
+ "l": 30,
127
+ "m": 31,
128
+ "n": 32,
129
+ "o": 33,
130
+ "p": 34,
131
+ "q": 35,
132
+ "r": 36,
133
+ "s": 37,
134
+ "t": 38,
135
+ "u": 39,
136
+ "v": 40,
137
+ "w": 41,
138
+ "x": 42,
139
+ "y": 43,
140
+ "z": 44,
141
+ "́": 45,
142
+ "̃": 46,
143
+ "̈": 47
144
+ },
145
+ "merges": []
146
+ }
147
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "clean_up_tokenization_spaces": true,
3
+ "cls_token": "[CLS]",
4
+ "mask_token": "[MASK]",
5
+ "model_max_length": 1000000000000000019884624838656,
6
+ "pad_token": "[PAD]",
7
+ "sep_token": "[SEP]",
8
+ "tokenizer_class": "PreTrainedTokenizerFast",
9
+ "unk_token": "[UNK]"
10
+ }