Hugging Face's logo

hunarbatra
/
CoVBERT

Fill-Mask Transformers PyTorch Safetensors roberta generated_from_trainer Inference Endpoints
Model card Files Community
2
hunarbatra commited on
Commit
285b026
•
1 Parent(s): 4206e0b

Upload tokenizer.json

Browse files
Files changed (1) hide show
  1. tokenizer.json +355 -0
tokenizer.json ADDED
@@ -0,0 +1,355 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": {
4
+ "direction": "Right",
5
+ "max_length": 1389,
6
+ "strategy": "LongestFirst",
7
+ "stride": 0
8
+ },
9
+ "padding": null,
10
+ "added_tokens": [
11
+ {
12
+ "id": 0,
13
+ "content": "<s>",
14
+ "single_word": false,
15
+ "lstrip": false,
16
+ "rstrip": false,
17
+ "normalized": true,
18
+ "special": true
19
+ },
20
+ {
21
+ "id": 1,
22
+ "content": "<pad>",
23
+ "single_word": false,
24
+ "lstrip": false,
25
+ "rstrip": false,
26
+ "normalized": true,
27
+ "special": true
28
+ },
29
+ {
30
+ "id": 2,
31
+ "content": "</s>",
32
+ "single_word": false,
33
+ "lstrip": false,
34
+ "rstrip": false,
35
+ "normalized": true,
36
+ "special": true
37
+ },
38
+ {
39
+ "id": 3,
40
+ "content": "<unk>",
41
+ "single_word": false,
42
+ "lstrip": false,
43
+ "rstrip": false,
44
+ "normalized": true,
45
+ "special": true
46
+ },
47
+ {
48
+ "id": 4,
49
+ "content": "<mask>",
50
+ "single_word": false,
51
+ "lstrip": true,
52
+ "rstrip": false,
53
+ "normalized": true,
54
+ "special": true
55
+ }
56
+ ],
57
+ "normalizer": null,
58
+ "pre_tokenizer": {
59
+ "type": "ByteLevel",
60
+ "add_prefix_space": false,
61
+ "trim_offsets": true,
62
+ "use_regex": true
63
+ },
64
+ "post_processor": {
65
+ "type": "RobertaProcessing",
66
+ "sep": [
67
+ "</s>",
68
+ 2
69
+ ],
70
+ "cls": [
71
+ "<s>",
72
+ 0
73
+ ],
74
+ "trim_offsets": true,
75
+ "add_prefix_space": false
76
+ },
77
+ "decoder": {
78
+ "type": "ByteLevel",
79
+ "add_prefix_space": true,
80
+ "trim_offsets": true,
81
+ "use_regex": true
82
+ },
83
+ "model": {
84
+ "type": "BPE",
85
+ "dropout": null,
86
+ "unk_token": null,
87
+ "continuing_subword_prefix": "",
88
+ "end_of_word_suffix": "",
89
+ "fuse_unk": false,
90
+ "vocab": {
91
+ "<s>": 0,
92
+ "<pad>": 1,
93
+ "</s>": 2,
94
+ "<unk>": 3,
95
+ "<mask>": 4,
96
+ "!": 5,
97
+ "\"": 6,
98
+ "#": 7,
99
+ "$": 8,
100
+ "%": 9,
101
+ "&": 10,
102
+ "'": 11,
103
+ "(": 12,
104
+ ")": 13,
105
+ "*": 14,
106
+ "+": 15,
107
+ ",": 16,
108
+ "-": 17,
109
+ ".": 18,
110
+ "/": 19,
111
+ "0": 20,
112
+ "1": 21,
113
+ "2": 22,
114
+ "3": 23,
115
+ "4": 24,
116
+ "5": 25,
117
+ "6": 26,
118
+ "7": 27,
119
+ "8": 28,
120
+ "9": 29,
121
+ ":": 30,
122
+ ";": 31,
123
+ "<": 32,
124
+ "=": 33,
125
+ ">": 34,
126
+ "?": 35,
127
+ "@": 36,
128
+ "A": 37,
129
+ "B": 38,
130
+ "C": 39,
131
+ "D": 40,
132
+ "E": 41,
133
+ "F": 42,
134
+ "G": 43,
135
+ "H": 44,
136
+ "I": 45,
137
+ "J": 46,
138
+ "K": 47,
139
+ "L": 48,
140
+ "M": 49,
141
+ "N": 50,
142
+ "O": 51,
143
+ "P": 52,
144
+ "Q": 53,
145
+ "R": 54,
146
+ "S": 55,
147
+ "T": 56,
148
+ "U": 57,
149
+ "V": 58,
150
+ "W": 59,
151
+ "X": 60,
152
+ "Y": 61,
153
+ "Z": 62,
154
+ "[": 63,
155
+ "\\": 64,
156
+ "]": 65,
157
+ "^": 66,
158
+ "_": 67,
159
+ "`": 68,
160
+ "a": 69,
161
+ "b": 70,
162
+ "c": 71,
163
+ "d": 72,
164
+ "e": 73,
165
+ "f": 74,
166
+ "g": 75,
167
+ "h": 76,
168
+ "i": 77,
169
+ "j": 78,
170
+ "k": 79,
171
+ "l": 80,
172
+ "m": 81,
173
+ "n": 82,
174
+ "o": 83,
175
+ "p": 84,
176
+ "q": 85,
177
+ "r": 86,
178
+ "s": 87,
179
+ "t": 88,
180
+ "u": 89,
181
+ "v": 90,
182
+ "w": 91,
183
+ "x": 92,
184
+ "y": 93,
185
+ "z": 94,
186
+ "{": 95,
187
+ "|": 96,
188
+ "}": 97,
189
+ "~": 98,
190
+ "¡": 99,
191
+ "¢": 100,
192
+ "£": 101,
193
+ "¤": 102,
194
+ "¥": 103,
195
+ "¦": 104,
196
+ "§": 105,
197
+ "¨": 106,
198
+ "©": 107,
199
+ "ª": 108,
200
+ "«": 109,
201
+ "¬": 110,
202
+ "®": 111,
203
+ "¯": 112,
204
+ "°": 113,
205
+ "±": 114,
206
+ "²": 115,
207
+ "³": 116,
208
+ "´": 117,
209
+ "µ": 118,
210
+ "¶": 119,
211
+ "·": 120,
212
+ "¸": 121,
213
+ "¹": 122,
214
+ "º": 123,
215
+ "»": 124,
216
+ "¼": 125,
217
+ "½": 126,
218
+ "¾": 127,
219
+ "¿": 128,
220
+ "À": 129,
221
+ "Á": 130,
222
+ "Â": 131,
223
+ "Ã": 132,
224
+ "Ä": 133,
225
+ "Å": 134,
226
+ "Æ": 135,
227
+ "Ç": 136,
228
+ "È": 137,
229
+ "É": 138,
230
+ "Ê": 139,
231
+ "Ë": 140,
232
+ "Ì": 141,
233
+ "Í": 142,
234
+ "Î": 143,
235
+ "Ï": 144,
236
+ "Ð": 145,
237
+ "Ñ": 146,
238
+ "Ò": 147,
239
+ "Ó": 148,
240
+ "Ô": 149,
241
+ "Õ": 150,
242
+ "Ö": 151,
243
+ "×": 152,
244
+ "Ø": 153,
245
+ "Ù": 154,
246
+ "Ú": 155,
247
+ "Û": 156,
248
+ "Ü": 157,
249
+ "Ý": 158,
250
+ "Þ": 159,
251
+ "ß": 160,
252
+ "à": 161,
253
+ "á": 162,
254
+ "â": 163,
255
+ "ã": 164,
256
+ "ä": 165,
257
+ "å": 166,
258
+ "æ": 167,
259
+ "ç": 168,
260
+ "è": 169,
261
+ "é": 170,
262
+ "ê": 171,
263
+ "ë": 172,
264
+ "ì": 173,
265
+ "í": 174,
266
+ "î": 175,
267
+ "ï": 176,
268
+ "ð": 177,
269
+ "ñ": 178,
270
+ "ò": 179,
271
+ "ó": 180,
272
+ "ô": 181,
273
+ "õ": 182,
274
+ "ö": 183,
275
+ "÷": 184,
276
+ "ø": 185,
277
+ "ù": 186,
278
+ "ú": 187,
279
+ "û": 188,
280
+ "ü": 189,
281
+ "ý": 190,
282
+ "þ": 191,
283
+ "ÿ": 192,
284
+ "��": 193,
285
+ "ā": 194,
286
+ "Ă": 195,
287
+ "ă": 196,
288
+ "Ą": 197,
289
+ "ą": 198,
290
+ "Ć": 199,
291
+ "ć": 200,
292
+ "Ĉ": 201,
293
+ "ĉ": 202,
294
+ "Ċ": 203,
295
+ "ċ": 204,
296
+ "Č": 205,
297
+ "č": 206,
298
+ "Ď": 207,
299
+ "ď": 208,
300
+ "Đ": 209,
301
+ "đ": 210,
302
+ "Ē": 211,
303
+ "ē": 212,
304
+ "Ĕ": 213,
305
+ "ĕ": 214,
306
+ "Ė": 215,
307
+ "ė": 216,
308
+ "Ę": 217,
309
+ "ę": 218,
310
+ "Ě": 219,
311
+ "ě": 220,
312
+ "Ĝ": 221,
313
+ "ĝ": 222,
314
+ "Ğ": 223,
315
+ "ğ": 224,
316
+ "Ġ": 225,
317
+ "ġ": 226,
318
+ "Ģ": 227,
319
+ "ģ": 228,
320
+ "Ĥ": 229,
321
+ "ĥ": 230,
322
+ "Ħ": 231,
323
+ "ħ": 232,
324
+ "Ĩ": 233,
325
+ "ĩ": 234,
326
+ "Ī": 235,
327
+ "ī": 236,
328
+ "Ĭ": 237,
329
+ "ĭ": 238,
330
+ "Į": 239,
331
+ "į": 240,
332
+ "İ": 241,
333
+ "ı": 242,
334
+ "IJ": 243,
335
+ "ij": 244,
336
+ "Ĵ": 245,
337
+ "ĵ": 246,
338
+ "Ķ": 247,
339
+ "ķ": 248,
340
+ "ĸ": 249,
341
+ "Ĺ": 250,
342
+ "ĺ": 251,
343
+ "Ļ": 252,
344
+ "ļ": 253,
345
+ "Ľ": 254,
346
+ "ľ": 255,
347
+ "Ŀ": 256,
348
+ "ŀ": 257,
349
+ "Ł": 258,
350
+ "ł": 259,
351
+ "Ń": 260
352
+ },
353
+ "merges": []
354
+ }
355
+ }