jeremylegrand commited on
Commit
bda0331
·
1 Parent(s): 03f88de

Upload tokenizer

Browse files
Files changed (4) hide show
  1. special_tokens_map.json +7 -0
  2. tokenizer.json +175 -0
  3. tokenizer_config.json +55 -0
  4. vocab.txt +25 -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 +1,175 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": null,
4
+ "padding": null,
5
+ "added_tokens": [
6
+ {
7
+ "id": 0,
8
+ "content": "[PAD]",
9
+ "single_word": false,
10
+ "lstrip": false,
11
+ "rstrip": false,
12
+ "normalized": false,
13
+ "special": true
14
+ },
15
+ {
16
+ "id": 1,
17
+ "content": "[UNK]",
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": "BertNormalizer",
54
+ "clean_text": true,
55
+ "handle_chinese_chars": true,
56
+ "strip_accents": null,
57
+ "lowercase": true
58
+ },
59
+ "pre_tokenizer": {
60
+ "type": "BertPreTokenizer"
61
+ },
62
+ "post_processor": {
63
+ "type": "TemplateProcessing",
64
+ "single": [
65
+ {
66
+ "SpecialToken": {
67
+ "id": "[CLS]",
68
+ "type_id": 0
69
+ }
70
+ },
71
+ {
72
+ "Sequence": {
73
+ "id": "A",
74
+ "type_id": 0
75
+ }
76
+ },
77
+ {
78
+ "SpecialToken": {
79
+ "id": "[SEP]",
80
+ "type_id": 0
81
+ }
82
+ }
83
+ ],
84
+ "pair": [
85
+ {
86
+ "SpecialToken": {
87
+ "id": "[CLS]",
88
+ "type_id": 0
89
+ }
90
+ },
91
+ {
92
+ "Sequence": {
93
+ "id": "A",
94
+ "type_id": 0
95
+ }
96
+ },
97
+ {
98
+ "SpecialToken": {
99
+ "id": "[SEP]",
100
+ "type_id": 0
101
+ }
102
+ },
103
+ {
104
+ "Sequence": {
105
+ "id": "B",
106
+ "type_id": 1
107
+ }
108
+ },
109
+ {
110
+ "SpecialToken": {
111
+ "id": "[SEP]",
112
+ "type_id": 1
113
+ }
114
+ }
115
+ ],
116
+ "special_tokens": {
117
+ "[CLS]": {
118
+ "id": "[CLS]",
119
+ "ids": [
120
+ 2
121
+ ],
122
+ "tokens": [
123
+ "[CLS]"
124
+ ]
125
+ },
126
+ "[SEP]": {
127
+ "id": "[SEP]",
128
+ "ids": [
129
+ 3
130
+ ],
131
+ "tokens": [
132
+ "[SEP]"
133
+ ]
134
+ }
135
+ }
136
+ },
137
+ "decoder": {
138
+ "type": "WordPiece",
139
+ "prefix": "##",
140
+ "cleanup": true
141
+ },
142
+ "model": {
143
+ "type": "WordPiece",
144
+ "unk_token": "[UNK]",
145
+ "continuing_subword_prefix": "##",
146
+ "max_input_chars_per_word": 100,
147
+ "vocab": {
148
+ "[PAD]": 0,
149
+ "[UNK]": 1,
150
+ "[CLS]": 2,
151
+ "[SEP]": 3,
152
+ "[MASK]": 4,
153
+ "a": 5,
154
+ "e": 6,
155
+ "i": 7,
156
+ "l": 8,
157
+ "m": 9,
158
+ "t": 10,
159
+ "##i": 11,
160
+ "##t": 12,
161
+ "##l": 13,
162
+ "##e": 14,
163
+ "##m": 15,
164
+ "##a": 16,
165
+ "em": 17,
166
+ "ti": 18,
167
+ "##il": 19,
168
+ "##tl": 20,
169
+ "##ail": 21,
170
+ "email": 22,
171
+ "titl": 23,
172
+ "title": 24
173
+ }
174
+ }
175
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[SEP]",
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": true,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": true,
47
+ "mask_token": "[MASK]",
48
+ "model_max_length": 512,
49
+ "pad_token": "[PAD]",
50
+ "sep_token": "[SEP]",
51
+ "strip_accents": null,
52
+ "tokenize_chinese_chars": true,
53
+ "tokenizer_class": "BertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
vocab.txt ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [PAD]
2
+ [UNK]
3
+ [CLS]
4
+ [SEP]
5
+ [MASK]
6
+ a
7
+ e
8
+ i
9
+ l
10
+ m
11
+ t
12
+ ##i
13
+ ##t
14
+ ##l
15
+ ##e
16
+ ##m
17
+ ##a
18
+ em
19
+ ti
20
+ ##il
21
+ ##tl
22
+ ##ail
23
+ email
24
+ titl
25
+ title