shyamsn97 commited on
Commit
afd27ca
1 Parent(s): 99cf917

Upload tokenizer

Browse files
Files changed (5) hide show
  1. merges.txt +1 -0
  2. special_tokens_map.json +15 -0
  3. tokenizer.json +350 -0
  4. tokenizer_config.json +24 -0
  5. vocab.json +1 -0
merges.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ #version: 0.2 - Trained by `huggingface/tokenizers`
special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
tokenizer.json ADDED
@@ -0,0 +1,350 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": null,
4
+ "padding": null,
5
+ "added_tokens": [
6
+ {
7
+ "id": 0,
8
+ "content": "<s>",
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": "</s>",
27
+ "single_word": false,
28
+ "lstrip": false,
29
+ "rstrip": false,
30
+ "normalized": false,
31
+ "special": true
32
+ },
33
+ {
34
+ "id": 3,
35
+ "content": "<unk>",
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": true,
47
+ "rstrip": false,
48
+ "normalized": false,
49
+ "special": true
50
+ }
51
+ ],
52
+ "normalizer": null,
53
+ "pre_tokenizer": {
54
+ "type": "ByteLevel",
55
+ "add_prefix_space": false,
56
+ "trim_offsets": true,
57
+ "use_regex": true
58
+ },
59
+ "post_processor": {
60
+ "type": "RobertaProcessing",
61
+ "sep": [
62
+ "</s>",
63
+ 2
64
+ ],
65
+ "cls": [
66
+ "<s>",
67
+ 0
68
+ ],
69
+ "trim_offsets": true,
70
+ "add_prefix_space": false
71
+ },
72
+ "decoder": {
73
+ "type": "ByteLevel",
74
+ "add_prefix_space": true,
75
+ "trim_offsets": true,
76
+ "use_regex": true
77
+ },
78
+ "model": {
79
+ "type": "BPE",
80
+ "dropout": null,
81
+ "unk_token": null,
82
+ "continuing_subword_prefix": "",
83
+ "end_of_word_suffix": "",
84
+ "fuse_unk": false,
85
+ "vocab": {
86
+ "<s>": 0,
87
+ "<pad>": 1,
88
+ "</s>": 2,
89
+ "<unk>": 3,
90
+ "<mask>": 4,
91
+ "!": 5,
92
+ "\"": 6,
93
+ "#": 7,
94
+ "$": 8,
95
+ "%": 9,
96
+ "&": 10,
97
+ "'": 11,
98
+ "(": 12,
99
+ ")": 13,
100
+ "*": 14,
101
+ "+": 15,
102
+ ",": 16,
103
+ "-": 17,
104
+ ".": 18,
105
+ "/": 19,
106
+ "0": 20,
107
+ "1": 21,
108
+ "2": 22,
109
+ "3": 23,
110
+ "4": 24,
111
+ "5": 25,
112
+ "6": 26,
113
+ "7": 27,
114
+ "8": 28,
115
+ "9": 29,
116
+ ":": 30,
117
+ ";": 31,
118
+ "<": 32,
119
+ "=": 33,
120
+ ">": 34,
121
+ "?": 35,
122
+ "@": 36,
123
+ "A": 37,
124
+ "B": 38,
125
+ "C": 39,
126
+ "D": 40,
127
+ "E": 41,
128
+ "F": 42,
129
+ "G": 43,
130
+ "H": 44,
131
+ "I": 45,
132
+ "J": 46,
133
+ "K": 47,
134
+ "L": 48,
135
+ "M": 49,
136
+ "N": 50,
137
+ "O": 51,
138
+ "P": 52,
139
+ "Q": 53,
140
+ "R": 54,
141
+ "S": 55,
142
+ "T": 56,
143
+ "U": 57,
144
+ "V": 58,
145
+ "W": 59,
146
+ "X": 60,
147
+ "Y": 61,
148
+ "Z": 62,
149
+ "[": 63,
150
+ "\\": 64,
151
+ "]": 65,
152
+ "^": 66,
153
+ "_": 67,
154
+ "`": 68,
155
+ "a": 69,
156
+ "b": 70,
157
+ "c": 71,
158
+ "d": 72,
159
+ "e": 73,
160
+ "f": 74,
161
+ "g": 75,
162
+ "h": 76,
163
+ "i": 77,
164
+ "j": 78,
165
+ "k": 79,
166
+ "l": 80,
167
+ "m": 81,
168
+ "n": 82,
169
+ "o": 83,
170
+ "p": 84,
171
+ "q": 85,
172
+ "r": 86,
173
+ "s": 87,
174
+ "t": 88,
175
+ "u": 89,
176
+ "v": 90,
177
+ "w": 91,
178
+ "x": 92,
179
+ "y": 93,
180
+ "z": 94,
181
+ "{": 95,
182
+ "|": 96,
183
+ "}": 97,
184
+ "~": 98,
185
+ "¡": 99,
186
+ "¢": 100,
187
+ "£": 101,
188
+ "¤": 102,
189
+ "¥": 103,
190
+ "¦": 104,
191
+ "§": 105,
192
+ "¨": 106,
193
+ "©": 107,
194
+ "ª": 108,
195
+ "«": 109,
196
+ "¬": 110,
197
+ "®": 111,
198
+ "¯": 112,
199
+ "°": 113,
200
+ "±": 114,
201
+ "²": 115,
202
+ "³": 116,
203
+ "´": 117,
204
+ "µ": 118,
205
+ "¶": 119,
206
+ "·": 120,
207
+ "¸": 121,
208
+ "¹": 122,
209
+ "º": 123,
210
+ "»": 124,
211
+ "¼": 125,
212
+ "½": 126,
213
+ "¾": 127,
214
+ "¿": 128,
215
+ "À": 129,
216
+ "Á": 130,
217
+ "Â": 131,
218
+ "Ã": 132,
219
+ "Ä": 133,
220
+ "Å": 134,
221
+ "Æ": 135,
222
+ "Ç": 136,
223
+ "È": 137,
224
+ "É": 138,
225
+ "Ê": 139,
226
+ "Ë": 140,
227
+ "Ì": 141,
228
+ "Í": 142,
229
+ "Î": 143,
230
+ "Ï": 144,
231
+ "Ð": 145,
232
+ "Ñ": 146,
233
+ "Ò": 147,
234
+ "Ó": 148,
235
+ "Ô": 149,
236
+ "Õ": 150,
237
+ "Ö": 151,
238
+ "×": 152,
239
+ "Ø": 153,
240
+ "Ù": 154,
241
+ "Ú": 155,
242
+ "Û": 156,
243
+ "Ü": 157,
244
+ "Ý": 158,
245
+ "Þ": 159,
246
+ "ß": 160,
247
+ "à": 161,
248
+ "á": 162,
249
+ "â": 163,
250
+ "ã": 164,
251
+ "ä": 165,
252
+ "å": 166,
253
+ "æ": 167,
254
+ "ç": 168,
255
+ "è": 169,
256
+ "é": 170,
257
+ "ê": 171,
258
+ "ë": 172,
259
+ "ì": 173,
260
+ "í": 174,
261
+ "î": 175,
262
+ "ï": 176,
263
+ "ð": 177,
264
+ "ñ": 178,
265
+ "ò": 179,
266
+ "ó": 180,
267
+ "ô": 181,
268
+ "õ": 182,
269
+ "ö": 183,
270
+ "÷": 184,
271
+ "ø": 185,
272
+ "ù": 186,
273
+ "ú": 187,
274
+ "û": 188,
275
+ "ü": 189,
276
+ "ý": 190,
277
+ "þ": 191,
278
+ "ÿ": 192,
279
+ "Ā": 193,
280
+ "ā": 194,
281
+ "Ă": 195,
282
+ "ă": 196,
283
+ "Ą": 197,
284
+ "ą": 198,
285
+ "Ć": 199,
286
+ "ć": 200,
287
+ "Ĉ": 201,
288
+ "ĉ": 202,
289
+ "Ċ": 203,
290
+ "ċ": 204,
291
+ "Č": 205,
292
+ "č": 206,
293
+ "Ď": 207,
294
+ "ď": 208,
295
+ "Đ": 209,
296
+ "đ": 210,
297
+ "Ē": 211,
298
+ "ē": 212,
299
+ "Ĕ": 213,
300
+ "ĕ": 214,
301
+ "Ė": 215,
302
+ "ė": 216,
303
+ "Ę": 217,
304
+ "ę": 218,
305
+ "Ě": 219,
306
+ "ě": 220,
307
+ "Ĝ": 221,
308
+ "ĝ": 222,
309
+ "Ğ": 223,
310
+ "ğ": 224,
311
+ "Ġ": 225,
312
+ "ġ": 226,
313
+ "Ģ": 227,
314
+ "ģ": 228,
315
+ "Ĥ": 229,
316
+ "ĥ": 230,
317
+ "Ħ": 231,
318
+ "ħ": 232,
319
+ "Ĩ": 233,
320
+ "ĩ": 234,
321
+ "Ī": 235,
322
+ "ī": 236,
323
+ "Ĭ": 237,
324
+ "ĭ": 238,
325
+ "Į": 239,
326
+ "į": 240,
327
+ "İ": 241,
328
+ "ı": 242,
329
+ "IJ": 243,
330
+ "ij": 244,
331
+ "Ĵ": 245,
332
+ "ĵ": 246,
333
+ "Ķ": 247,
334
+ "ķ": 248,
335
+ "ĸ": 249,
336
+ "Ĺ": 250,
337
+ "ĺ": 251,
338
+ "Ļ": 252,
339
+ "ļ": 253,
340
+ "Ľ": 254,
341
+ "ľ": 255,
342
+ "Ŀ": 256,
343
+ "ŀ": 257,
344
+ "Ł": 258,
345
+ "ł": 259,
346
+ "Ń": 260
347
+ },
348
+ "merges": []
349
+ }
350
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<s>",
4
+ "cls_token": "<s>",
5
+ "eos_token": "</s>",
6
+ "errors": "replace",
7
+ "fast": true,
8
+ "mask_token": {
9
+ "__type": "AddedToken",
10
+ "content": "<mask>",
11
+ "lstrip": true,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "model_max_length": 512,
17
+ "name_or_path": "distilroberta-base",
18
+ "pad_token": "<pad>",
19
+ "sep_token": "</s>",
20
+ "special_tokens_map_file": null,
21
+ "tokenizer_class": "RobertaTokenizer",
22
+ "trim_offsets": true,
23
+ "unk_token": "<unk>"
24
+ }
vocab.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"<s>":0,"<pad>":1,"</s>":2,"<unk>":3,"<mask>":4,"!":5,"\"":6,"#":7,"$":8,"%":9,"&":10,"'":11,"(":12,")":13,"*":14,"+":15,",":16,"-":17,".":18,"/":19,"0":20,"1":21,"2":22,"3":23,"4":24,"5":25,"6":26,"7":27,"8":28,"9":29,":":30,";":31,"<":32,"=":33,">":34,"?":35,"@":36,"A":37,"B":38,"C":39,"D":40,"E":41,"F":42,"G":43,"H":44,"I":45,"J":46,"K":47,"L":48,"M":49,"N":50,"O":51,"P":52,"Q":53,"R":54,"S":55,"T":56,"U":57,"V":58,"W":59,"X":60,"Y":61,"Z":62,"[":63,"\\":64,"]":65,"^":66,"_":67,"`":68,"a":69,"b":70,"c":71,"d":72,"e":73,"f":74,"g":75,"h":76,"i":77,"j":78,"k":79,"l":80,"m":81,"n":82,"o":83,"p":84,"q":85,"r":86,"s":87,"t":88,"u":89,"v":90,"w":91,"x":92,"y":93,"z":94,"{":95,"|":96,"}":97,"~":98,"¡":99,"¢":100,"£":101,"¤":102,"¥":103,"¦":104,"§":105,"¨":106,"©":107,"ª":108,"«":109,"¬":110,"®":111,"¯":112,"°":113,"±":114,"²":115,"³":116,"´":117,"µ":118,"¶":119,"·":120,"¸":121,"¹":122,"º":123,"»":124,"¼":125,"½":126,"¾":127,"¿":128,"À":129,"Á":130,"Â":131,"Ã":132,"Ä":133,"Å":134,"Æ":135,"Ç":136,"È":137,"É":138,"Ê":139,"Ë":140,"Ì":141,"Í":142,"Î":143,"Ï":144,"Ð":145,"Ñ":146,"Ò":147,"Ó":148,"Ô":149,"Õ":150,"Ö":151,"×":152,"Ø":153,"Ù":154,"Ú":155,"Û":156,"Ü":157,"Ý":158,"Þ":159,"ß":160,"à":161,"á":162,"â":163,"ã":164,"ä":165,"å":166,"æ":167,"ç":168,"è":169,"é":170,"ê":171,"ë":172,"ì":173,"í":174,"î":175,"ï":176,"ð":177,"ñ":178,"ò":179,"ó":180,"ô":181,"õ":182,"ö":183,"÷":184,"ø":185,"ù":186,"ú":187,"û":188,"ü":189,"ý":190,"þ":191,"ÿ":192,"Ā":193,"ā":194,"Ă":195,"ă":196,"Ą":197,"ą":198,"Ć":199,"ć":200,"Ĉ":201,"ĉ":202,"Ċ":203,"ċ":204,"Č":205,"č":206,"Ď":207,"ď":208,"Đ":209,"đ":210,"Ē":211,"ē":212,"Ĕ":213,"ĕ":214,"Ė":215,"ė":216,"Ę":217,"ę":218,"Ě":219,"ě":220,"Ĝ":221,"ĝ":222,"Ğ":223,"ğ":224,"Ġ":225,"ġ":226,"Ģ":227,"ģ":228,"Ĥ":229,"ĥ":230,"Ħ":231,"ħ":232,"Ĩ":233,"ĩ":234,"Ī":235,"ī":236,"Ĭ":237,"ĭ":238,"Į":239,"į":240,"İ":241,"ı":242,"IJ":243,"ij":244,"Ĵ":245,"ĵ":246,"Ķ":247,"ķ":248,"ĸ":249,"Ĺ":250,"ĺ":251,"Ļ":252,"ļ":253,"Ľ":254,"ľ":255,"Ŀ":256,"ŀ":257,"Ł":258,"ł":259,"Ń":260}