Marxav commited on
Commit
4d82991
1 Parent(s): 9ccf011

add tokenizer

Browse files
Files changed (3) hide show
  1. added_tokens.json +1 -1
  2. tokenizer.json +137 -138
  3. vocab.json +1 -1
added_tokens.json CHANGED
@@ -1 +1 @@
1
- {"<": 255, ">": 254, "#": 256}
 
1
+ {"<": 254, ">": 253, "#": 255}
tokenizer.json CHANGED
@@ -13,7 +13,7 @@
13
  "special": true
14
  },
15
  {
16
- "id": 254,
17
  "content": ">",
18
  "single_word": false,
19
  "lstrip": false,
@@ -22,7 +22,7 @@
22
  "special": true
23
  },
24
  {
25
- "id": 255,
26
  "content": "<",
27
  "single_word": false,
28
  "lstrip": false,
@@ -31,7 +31,7 @@
31
  "special": true
32
  },
33
  {
34
- "id": 256,
35
  "content": "#",
36
  "single_word": false,
37
  "lstrip": false,
@@ -183,141 +183,140 @@
183
  "É": 116,
184
  "Ê": 117,
185
  "Ì": 118,
186
- "Í": 119,
187
- "Î": 120,
188
- "Ï": 121,
189
- "Ð": 122,
190
- "Ô": 123,
191
- "Ö": 124,
192
- "×": 125,
193
- "Ü": 126,
194
- "ß": 127,
195
- "à": 128,
196
- "á": 129,
197
- "â": 130,
198
- "ã": 131,
199
- "ä": 132,
200
- "å": 133,
201
- "æ": 134,
202
- "ç": 135,
203
- "è": 136,
204
- "é": 137,
205
- "ê": 138,
206
- "ë": 139,
207
- "ì": 140,
208
- "í": 141,
209
- "î": 142,
210
- "ï": 143,
211
- "ñ": 144,
212
- "ò": 145,
213
- "ó": 146,
214
- "ô": 147,
215
- "õ": 148,
216
- "ö": 149,
217
- "ø": 150,
218
- "ù": 151,
219
- "ú": 152,
220
- "û": 153,
221
- "ü": 154,
222
- "ý": 155,
223
- "ÿ": 156,
224
- "ā": 157,
225
- "ć": 158,
226
- "č": 159,
227
- "Ğ": 160,
228
- "ğ": 161,
229
- "Ġ": 162,
230
- "Ģ": 163,
231
- "ģ": 164,
232
- "Ĥ": 165,
233
- "ĥ": 166,
234
- "Ĩ": 167,
235
- "ĩ": 168,
236
- "Ī": 169,
237
- "ī": 170,
238
- "Ĭ": 171,
239
- "ĭ": 172,
240
- "į": 173,
241
- "İ": 174,
242
- "ı": 175,
243
- "IJ": 176,
244
- "ij": 177,
245
- "Ĵ": 178,
246
- "ĵ": 179,
247
- "Ķ": 180,
248
- "ĸ": 181,
249
- "Ĺ": 182,
250
- "ĺ": 183,
251
- "Ļ": 184,
252
- "ļ": 185,
253
- "Ľ": 186,
254
- "ľ": 187,
255
- "Ŀ": 188,
256
- "ŀ": 189,
257
- "Ł": 190,
258
- "ł": 191,
259
- "Ń": 192,
260
- "ŋ": 193,
261
- "ō": 194,
262
- "Œ": 195,
263
- "œ": 196,
264
- "Ś": 197,
265
- "ŝ": 198,
266
- "Ş": 199,
267
- "ş": 200,
268
- "š": 201,
269
- "ū": 202,
270
- "ŵ": 203,
271
- "ź": 204,
272
- "Ž": 205,
273
- "ž": 206,
274
- "ǘ": 207,
275
- "ȝ": 208,
276
- "ɑ": 209,
277
- "ɔ": 210,
278
- "ə": 211,
279
- "ɛ": 212,
280
- "ɡ": 213,
281
- "ɣ": 214,
282
- "ɥ": 215,
283
- "ɨ": 216,
284
- "ɩ": 217,
285
- "ɲ": 218,
286
- "ʁ": 219,
287
- "ʃ": 220,
288
- "ʋ": 221,
289
- "ʒ": 222,
290
- "ʔ": 223,
291
- "ʻ": 224,
292
- "ʼ": 225,
293
- "ʾ": 226,
294
- "ʿ": 227,
295
- "́": 228,
296
- "̃": 229,
297
- "̐": 230,
298
- "̓": 231,
299
- "͠": 232,
300
- "Δ": 233,
301
- "α": 234,
302
- "β": 235,
303
- "μ": 236,
304
- "σ": 237,
305
- "а": 238,
306
- "е": 239,
307
- "": 240,
308
- "": 241,
309
- "": 242,
310
- "": 243,
311
- "": 244,
312
- "": 245,
313
- "": 246,
314
- "": 247,
315
- "": 248,
316
- "": 249,
317
- "": 250,
318
- "": 251,
319
- "": 252,
320
- "∴": 253
321
  },
322
  "merges": []
323
  }
 
13
  "special": true
14
  },
15
  {
16
+ "id": 253,
17
  "content": ">",
18
  "single_word": false,
19
  "lstrip": false,
 
22
  "special": true
23
  },
24
  {
25
+ "id": 254,
26
  "content": "<",
27
  "single_word": false,
28
  "lstrip": false,
 
31
  "special": true
32
  },
33
  {
34
+ "id": 255,
35
  "content": "#",
36
  "single_word": false,
37
  "lstrip": false,
 
183
  "É": 116,
184
  "Ê": 117,
185
  "Ì": 118,
186
+ "Î": 119,
187
+ "Ï": 120,
188
+ "Ð": 121,
189
+ "Ô": 122,
190
+ "Ö": 123,
191
+ "×": 124,
192
+ "Ü": 125,
193
+ "ß": 126,
194
+ "à": 127,
195
+ "á": 128,
196
+ "â": 129,
197
+ "ã": 130,
198
+ "ä": 131,
199
+ "å": 132,
200
+ "æ": 133,
201
+ "ç": 134,
202
+ "è": 135,
203
+ "é": 136,
204
+ "ê": 137,
205
+ "ë": 138,
206
+ "ì": 139,
207
+ "í": 140,
208
+ "î": 141,
209
+ "ï": 142,
210
+ "ñ": 143,
211
+ "ò": 144,
212
+ "ó": 145,
213
+ "ô": 146,
214
+ "õ": 147,
215
+ "ö": 148,
216
+ "ø": 149,
217
+ "ù": 150,
218
+ "ú": 151,
219
+ "û": 152,
220
+ "ü": 153,
221
+ "ý": 154,
222
+ "ÿ": 155,
223
+ "ā": 156,
224
+ "ć": 157,
225
+ "č": 158,
226
+ "Ğ": 159,
227
+ "ğ": 160,
228
+ "Ġ": 161,
229
+ "Ģ": 162,
230
+ "ģ": 163,
231
+ "Ĥ": 164,
232
+ "ĥ": 165,
233
+ "Ĩ": 166,
234
+ "ĩ": 167,
235
+ "Ī": 168,
236
+ "ī": 169,
237
+ "Ĭ": 170,
238
+ "ĭ": 171,
239
+ "į": 172,
240
+ "İ": 173,
241
+ "ı": 174,
242
+ "IJ": 175,
243
+ "ij": 176,
244
+ "Ĵ": 177,
245
+ "ĵ": 178,
246
+ "Ķ": 179,
247
+ "ĸ": 180,
248
+ "Ĺ": 181,
249
+ "ĺ": 182,
250
+ "Ļ": 183,
251
+ "ļ": 184,
252
+ "Ľ": 185,
253
+ "ľ": 186,
254
+ "Ŀ": 187,
255
+ "ŀ": 188,
256
+ "Ł": 189,
257
+ "ł": 190,
258
+ "Ń": 191,
259
+ "ŋ": 192,
260
+ "ō": 193,
261
+ "Œ": 194,
262
+ "œ": 195,
263
+ "Ś": 196,
264
+ "ŝ": 197,
265
+ "Ş": 198,
266
+ "ş": 199,
267
+ "š": 200,
268
+ "ū": 201,
269
+ "ŵ": 202,
270
+ "ź": 203,
271
+ "Ž": 204,
272
+ "ž": 205,
273
+ "ǘ": 206,
274
+ "ȝ": 207,
275
+ "ɑ": 208,
276
+ "ɔ": 209,
277
+ "ə": 210,
278
+ "ɛ": 211,
279
+ "ɡ": 212,
280
+ "ɣ": 213,
281
+ "ɥ": 214,
282
+ "ɨ": 215,
283
+ "ɩ": 216,
284
+ "ɲ": 217,
285
+ "ʁ": 218,
286
+ "ʃ": 219,
287
+ "ʋ": 220,
288
+ "ʒ": 221,
289
+ "ʔ": 222,
290
+ "ʻ": 223,
291
+ "ʼ": 224,
292
+ "ʾ": 225,
293
+ "ʿ": 226,
294
+ "́": 227,
295
+ "̃": 228,
296
+ "̐": 229,
297
+ "̓": 230,
298
+ "͠": 231,
299
+ "Δ": 232,
300
+ "α": 233,
301
+ "β": 234,
302
+ "μ": 235,
303
+ "σ": 236,
304
+ "а": 237,
305
+ "е": 238,
306
+ "": 239,
307
+ "": 240,
308
+ "": 241,
309
+ "": 242,
310
+ "": 243,
311
+ "": 244,
312
+ "": 245,
313
+ "": 246,
314
+ "": 247,
315
+ "": 248,
316
+ "": 249,
317
+ "": 250,
318
+ "": 251,
319
+ "": 252
 
320
  },
321
  "merges": []
322
  }
vocab.json CHANGED
@@ -1 +1 @@
1
- {"<|endoftext|>":0,"\n":1," ":2,"!":3,"&":4,"'":5,"(":6,")":7,"*":8,"+":9,"-":10,".":11,"/":12,"0":13,"1":14,"2":15,"3":16,"4":17,"5":18,"6":19,"7":20,"8":21,"9":22,":":23,";":24,"@":25,"A":26,"B":27,"C":28,"D":29,"E":30,"F":31,"G":32,"H":33,"I":34,"J":35,"K":36,"L":37,"M":38,"N":39,"O":40,"P":41,"Q":42,"R":43,"S":44,"T":45,"U":46,"V":47,"W":48,"X":49,"Y":50,"Z":51,"a":52,"b":53,"c":54,"d":55,"e":56,"f":57,"g":58,"h":59,"i":60,"j":61,"k":62,"l":63,"m":64,"n":65,"o":66,"p":67,"q":68,"r":69,"s":70,"t":71,"u":72,"v":73,"w":74,"x":75,"y":76,"z":77,"¡":78,"¢":79,"£":80,"¤":81,"¥":82,"¦":83,"§":84,"¨":85,"©":86,"ª":87,"«":88,"¬":89,"®":90,"¯":91,"°":92,"±":93,"²":94,"³":95,"´":96,"µ":97,"¶":98,"·":99,"¸":100,"¹":101,"º":102,"»":103,"¼":104,"½":105,"¾":106,"¿":107,"Á":108,"Â":109,"Ã":110,"Ä":111,"Å":112,"Æ":113,"Ç":114,"È":115,"É":116,"Ê":117,"Ì":118,"Í":119,"Î":120,"Ï":121,"Ð":122,"Ô":123,"Ö":124,"×":125,"Ü":126,"ß":127,"à":128,"á":129,"â":130,"ã":131,"ä":132,"å":133,"æ":134,"ç":135,"è":136,"é":137,"ê":138,"ë":139,"ì":140,"í":141,"î":142,"ï":143,"ñ":144,"ò":145,"ó":146,"ô":147,"õ":148,"ö":149,"ø":150,"ù":151,"ú":152,"û":153,"ü":154,"ý":155,"ÿ":156,"ā":157,"ć":158,"č":159,"Ğ":160,"ğ":161,"Ġ":162,"Ģ":163,"ģ":164,"Ĥ":165,"ĥ":166,"Ĩ":167,"ĩ":168,"Ī":169,"ī":170,"Ĭ":171,"ĭ":172,"į":173,"İ":174,"ı":175,"IJ":176,"ij":177,"Ĵ":178,"ĵ":179,"Ķ":180,"ĸ":181,"Ĺ":182,"ĺ":183,"Ļ":184,"ļ":185,"Ľ":186,"ľ":187,"Ŀ":188,"ŀ":189,"Ł":190,"ł":191,"Ń":192,"ŋ":193,"ō":194,"Œ":195,"œ":196,"Ś":197,"ŝ":198,"Ş":199,"ş":200,"š":201,"ū":202,"ŵ":203,"ź":204,"Ž":205,"ž":206,"ǘ":207,"ȝ":208,"ɑ":209,"ɔ":210,"ə":211,"ɛ":212,"ɡ":213,"ɣ":214,"ɥ":215,"ɨ":216,"ɩ":217,"ɲ":218,"ʁ":219,"ʃ":220,"ʋ":221,"ʒ":222,"ʔ":223,"ʻ":224,"ʼ":225,"ʾ":226,"ʿ":227,"́":228,"̃":229,"̐":230,"̓":231,"͠":232,"Δ":233,"α":234,"β":235,"μ":236,"σ":237,"а":238,"е":239,"":240,"":241,"":242,"":243,"":244,"":245,"":246,"":247,"":248,"":249,"":250,"":251,"":252,"∴":253}
 
1
+ {"<|endoftext|>":0,"\n":1," ":2,"!":3,"&":4,"'":5,"(":6,")":7,"*":8,"+":9,"-":10,".":11,"/":12,"0":13,"1":14,"2":15,"3":16,"4":17,"5":18,"6":19,"7":20,"8":21,"9":22,":":23,";":24,"@":25,"A":26,"B":27,"C":28,"D":29,"E":30,"F":31,"G":32,"H":33,"I":34,"J":35,"K":36,"L":37,"M":38,"N":39,"O":40,"P":41,"Q":42,"R":43,"S":44,"T":45,"U":46,"V":47,"W":48,"X":49,"Y":50,"Z":51,"a":52,"b":53,"c":54,"d":55,"e":56,"f":57,"g":58,"h":59,"i":60,"j":61,"k":62,"l":63,"m":64,"n":65,"o":66,"p":67,"q":68,"r":69,"s":70,"t":71,"u":72,"v":73,"w":74,"x":75,"y":76,"z":77,"¡":78,"¢":79,"£":80,"¤":81,"¥":82,"¦":83,"§":84,"¨":85,"©":86,"ª":87,"«":88,"¬":89,"®":90,"¯":91,"°":92,"±":93,"²":94,"³":95,"´":96,"µ":97,"¶":98,"·":99,"¸":100,"¹":101,"º":102,"»":103,"¼":104,"½":105,"¾":106,"¿":107,"Á":108,"Â":109,"Ã":110,"Ä":111,"Å":112,"Æ":113,"Ç":114,"È":115,"É":116,"Ê":117,"Ì":118,"Î":119,"Ï":120,"Ð":121,"Ô":122,"Ö":123,"×":124,"Ü":125,"ß":126,"à":127,"á":128,"â":129,"ã":130,"ä":131,"å":132,"æ":133,"ç":134,"è":135,"é":136,"ê":137,"ë":138,"ì":139,"í":140,"î":141,"ï":142,"ñ":143,"ò":144,"ó":145,"ô":146,"õ":147,"ö":148,"ø":149,"ù":150,"ú":151,"û":152,"ü":153,"ý":154,"ÿ":155,"ā":156,"ć":157,"č":158,"Ğ":159,"ğ":160,"Ġ":161,"Ģ":162,"ģ":163,"Ĥ":164,"ĥ":165,"Ĩ":166,"ĩ":167,"Ī":168,"ī":169,"Ĭ":170,"ĭ":171,"į":172,"İ":173,"ı":174,"IJ":175,"ij":176,"Ĵ":177,"ĵ":178,"Ķ":179,"ĸ":180,"Ĺ":181,"ĺ":182,"Ļ":183,"ļ":184,"Ľ":185,"ľ":186,"Ŀ":187,"ŀ":188,"Ł":189,"ł":190,"Ń":191,"ŋ":192,"ō":193,"Œ":194,"œ":195,"Ś":196,"ŝ":197,"Ş":198,"ş":199,"š":200,"ū":201,"ŵ":202,"ź":203,"Ž":204,"ž":205,"ǘ":206,"ȝ":207,"ɑ":208,"ɔ":209,"ə":210,"ɛ":211,"ɡ":212,"ɣ":213,"ɥ":214,"ɨ":215,"ɩ":216,"ɲ":217,"ʁ":218,"ʃ":219,"ʋ":220,"ʒ":221,"ʔ":222,"ʻ":223,"ʼ":224,"ʾ":225,"ʿ":226,"́":227,"̃":228,"̐":229,"̓":230,"͠":231,"Δ":232,"α":233,"β":234,"μ":235,"σ":236,"а":237,"е":238,"":239,"":240,"":241,"":242,"":243,"":244,"":245,"":246,"":247,"":248,"":249,"":250,"":251,"":252}