Hugging Face's logo

tf-tpu
/
unigram-tokenizer-wikitext

Model card Files Community
1
sayakpaul HF staff commited on
Commit
99b7b7b
·
1 Parent(s): 979e21e

add tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +1 -0
  2. tokenizer.json +198 -0
  3. tokenizer_config.json +1 -0
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "<unk>", "sep_token": "[SEP]", "pad_token": "<pad>", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}
tokenizer.json ADDED
@@ -0,0 +1,198 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": null,
4
+ "padding": null,
5
+ "added_tokens": [
6
+ {
7
+ "id": 0,
8
+ "content": "[CLS]",
9
+ "single_word": false,
10
+ "lstrip": false,
11
+ "rstrip": false,
12
+ "normalized": false,
13
+ "special": true
14
+ },
15
+ {
16
+ "id": 1,
17
+ "content": "[SEP]",
18
+ "single_word": false,
19
+ "lstrip": false,
20
+ "rstrip": false,
21
+ "normalized": false,
22
+ "special": true
23
+ },
24
+ {
25
+ "id": 2,
26
+ "content": "<unk>",
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": {
53
+ "type": "Sequence",
54
+ "normalizers": [
55
+ {
56
+ "type": "Replace",
57
+ "pattern": {
58
+ "String": "``"
59
+ },
60
+ "content": "\""
61
+ },
62
+ {
63
+ "type": "Replace",
64
+ "pattern": {
65
+ "String": "''"
66
+ },
67
+ "content": "\""
68
+ }
69
+ ]
70
+ },
71
+ "pre_tokenizer": {
72
+ "type": "Metaspace",
73
+ "replacement": "▁",
74
+ "add_prefix_space": true
75
+ },
76
+ "post_processor": {
77
+ "type": "TemplateProcessing",
78
+ "single": [
79
+ {
80
+ "SpecialToken": {
81
+ "id": "[CLS]",
82
+ "type_id": 0
83
+ }
84
+ },
85
+ {
86
+ "Sequence": {
87
+ "id": "A",
88
+ "type_id": 0
89
+ }
90
+ },
91
+ {
92
+ "SpecialToken": {
93
+ "id": "[SEP]",
94
+ "type_id": 0
95
+ }
96
+ }
97
+ ],
98
+ "pair": [
99
+ {
100
+ "SpecialToken": {
101
+ "id": "[CLS]",
102
+ "type_id": 0
103
+ }
104
+ },
105
+ {
106
+ "Sequence": {
107
+ "id": "A",
108
+ "type_id": 0
109
+ }
110
+ },
111
+ {
112
+ "SpecialToken": {
113
+ "id": "[SEP]",
114
+ "type_id": 0
115
+ }
116
+ },
117
+ {
118
+ "Sequence": {
119
+ "id": "B",
120
+ "type_id": 1
121
+ }
122
+ },
123
+ {
124
+ "SpecialToken": {
125
+ "id": "[SEP]",
126
+ "type_id": 1
127
+ }
128
+ }
129
+ ],
130
+ "special_tokens": {
131
+ "[CLS]": {
132
+ "id": "[CLS]",
133
+ "ids": [
134
+ 0
135
+ ],
136
+ "tokens": [
137
+ "[CLS]"
138
+ ]
139
+ },
140
+ "[SEP]": {
141
+ "id": "[SEP]",
142
+ "ids": [
143
+ 1
144
+ ],
145
+ "tokens": [
146
+ "[SEP]"
147
+ ]
148
+ }
149
+ }
150
+ },
151
+ "decoder": {
152
+ "type": "Metaspace",
153
+ "replacement": "▁",
154
+ "add_prefix_space": true
155
+ },
156
+ "model": {
157
+ "type": "Unigram",
158
+ "unk_id": 2,
159
+ "vocab": [
160
+ [
161
+ "[CLS]",
162
+ 0.0
163
+ ],
164
+ [
165
+ "[SEP]",
166
+ 0.0
167
+ ],
168
+ [
169
+ "<unk>",
170
+ 0.0
171
+ ],
172
+ [
173
+ "<pad>",
174
+ 0.0
175
+ ],
176
+ [
177
+ "[MASK]",
178
+ 0.0
179
+ ],
180
+ [
181
+ "t",
182
+ -0.9163739781069129
183
+ ],
184
+ [
185
+ "x",
186
+ -1.6096599126533642
187
+ ],
188
+ [
189
+ "e",
190
+ -1.6096599126533642
191
+ ],
192
+ [
193
+ "▁",
194
+ -1.6096599126533642
195
+ ]
196
+ ]
197
+ }
198
+ }
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"do_lower_case": true, "remove_space": true, "keep_accents": false, "bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "<unk>", "sep_token": "[SEP]", "pad_token": "<pad>", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false, "__type": "AddedToken"}, "tokenizer_class": "AlbertTokenizer"}