Zaid commited on
Commit
d35de3e
1 Parent(s): d3f1780

Upload tokenizer

Browse files
Files changed (2) hide show
  1. tokenizer.json +66 -136
  2. vocab.json +1 -1
tokenizer.json CHANGED
@@ -229,142 +229,72 @@
229
  "<|meter_13|>": 18,
230
  "<|meter_14|>": 19,
231
  "<|meter_15|>": 20,
232
- "\t": 21,
233
- " ": 22,
234
- "!": 23,
235
- "\"": 24,
236
- "#": 25,
237
- "(": 26,
238
- ")": 27,
239
- "*": 28,
240
- ",": 29,
241
- "-": 30,
242
- ".": 31,
243
- "/": 32,
244
- "0": 33,
245
- "1": 34,
246
- "2": 35,
247
- "3": 36,
248
- "4": 37,
249
- "5": 38,
250
- "6": 39,
251
- "7": 40,
252
- "8": 41,
253
- "9": 42,
254
- ":": 43,
255
- ";": 44,
256
- "<": 45,
257
- "=": 46,
258
- ">": 47,
259
- "?": 48,
260
- "G": 49,
261
- "H": 50,
262
- "I": 51,
263
- "P": 52,
264
- "R": 53,
265
- "T": 54,
266
- "[": 55,
267
- "]": 56,
268
- "_": 57,
269
- "a": 58,
270
- "b": 59,
271
- "c": 60,
272
- "e": 61,
273
- "f": 62,
274
- "g": 63,
275
- "h": 64,
276
- "i": 65,
277
- "l": 66,
278
- "m": 67,
279
- "n": 68,
280
- "p": 69,
281
- "r": 70,
282
- "s": 71,
283
- "t": 72,
284
- "v": 73,
285
- "x": 74,
286
- "y": 75,
287
- "|": 76,
288
- "}": 77,
289
- "~": 78,
290
- " ": 79,
291
- "£": 80,
292
- "§": 81,
293
- "«": 82,
294
- "±": 83,
295
- "´": 84,
296
- "·": 85,
297
- "»": 86,
298
- "×": 87,
299
- "ˆ": 88,
300
- "،": 89,
301
- "؛": 90,
302
- "؟": 91,
303
- "ء": 92,
304
- "آ": 93,
305
- "أ": 94,
306
- "ؤ": 95,
307
- "إ": 96,
308
- "ئ": 97,
309
- "ا": 98,
310
- "ب": 99,
311
- "ة": 100,
312
- "ت": 101,
313
- "ث": 102,
314
- "ج": 103,
315
- "ح": 104,
316
- "خ": 105,
317
- "د": 106,
318
- "ذ": 107,
319
- "ر": 108,
320
- "ز": 109,
321
- "س": 110,
322
- "ش": 111,
323
- "ص": 112,
324
- "ض": 113,
325
- "ط": 114,
326
- "ظ": 115,
327
- "ع": 116,
328
- "غ": 117,
329
- "ف": 118,
330
- "ق": 119,
331
- "ك": 120,
332
- "ل": 121,
333
- "م": 122,
334
- "ن": 123,
335
- "ه": 124,
336
- "و": 125,
337
- "ى": 126,
338
- "ي": 127,
339
- "ً": 128,
340
- "ٌ": 129,
341
- "ٍ": 130,
342
- "َ": 131,
343
- "ُ": 132,
344
- "ِ": 133,
345
- "ّ": 134,
346
- "ْ": 135,
347
- "ٓ": 136,
348
- "٤": 137,
349
- "٩": 138,
350
- "ٹ": 139,
351
- "ک": 140,
352
- "ی": 141,
353
- "‌": 142,
354
- "‍": 143,
355
- "‏": 144,
356
- "–": 145,
357
- "“": 146,
358
- "”": 147,
359
- "„": 148,
360
- "†": 149,
361
- "…": 150,
362
- "": 151,
363
- "": 152,
364
- "": 153,
365
- "": 154,
366
- "ﺑ": 155,
367
- "�": 156
368
  },
369
  "merges": []
370
  }
 
229
  "<|meter_13|>": 18,
230
  "<|meter_14|>": 19,
231
  "<|meter_15|>": 20,
232
+ " ": 21,
233
+ "0": 22,
234
+ "1": 23,
235
+ "2": 24,
236
+ "3": 25,
237
+ "4": 26,
238
+ "5": 27,
239
+ "6": 28,
240
+ "7": 29,
241
+ "8": 30,
242
+ "9": 31,
243
+ "<": 32,
244
+ ">": 33,
245
+ "_": 34,
246
+ "b": 35,
247
+ "e": 36,
248
+ "m": 37,
249
+ "p": 38,
250
+ "r": 39,
251
+ "s": 40,
252
+ "t": 41,
253
+ "v": 42,
254
+ "|": 43,
255
+ "~": 44,
256
+ "ء": 45,
257
+ "أ": 46,
258
+ "ؤ": 47,
259
+ "ئ": 48,
260
+ "ا": 49,
261
+ "ب": 50,
262
+ "ة": 51,
263
+ "ت": 52,
264
+ "ث": 53,
265
+ "ج": 54,
266
+ "ح": 55,
267
+ "خ": 56,
268
+ "د": 57,
269
+ "ذ": 58,
270
+ "ر": 59,
271
+ "ز": 60,
272
+ "س": 61,
273
+ "ش": 62,
274
+ "ص": 63,
275
+ "ض": 64,
276
+ "ط": 65,
277
+ "ظ": 66,
278
+ "ع": 67,
279
+ "غ": 68,
280
+ "ف": 69,
281
+ "ق": 70,
282
+ "ك": 71,
283
+ "ل": 72,
284
+ "م": 73,
285
+ "ن": 74,
286
+ "ه": 75,
287
+ "و": 76,
288
+ "ى": 77,
289
+ "ي": 78,
290
+ "ً": 79,
291
+ "ٌ": 80,
292
+ "ٍ": 81,
293
+ "َ": 82,
294
+ "ُ": 83,
295
+ "ِ": 84,
296
+ "ّ": 85,
297
+ "ْ": 86
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
298
  },
299
  "merges": []
300
  }
vocab.json CHANGED
@@ -1 +1 @@
1
- {"<|endoftext|>":0,"<|vsep|>":1,"<|bsep|>":2,"<|pad|>":3,"<|psep|>":4,"<|meter_0|>":5,"<|meter_1|>":6,"<|meter_2|>":7,"<|meter_3|>":8,"<|meter_4|>":9,"<|meter_5|>":10,"<|meter_6|>":11,"<|meter_7|>":12,"<|meter_8|>":13,"<|meter_9|>":14,"<|meter_10|>":15,"<|meter_11|>":16,"<|meter_12|>":17,"<|meter_13|>":18,"<|meter_14|>":19,"<|meter_15|>":20,"\t":21," ":22,"!":23,"\"":24,"#":25,"(":26,")":27,"*":28,",":29,"-":30,".":31,"/":32,"0":33,"1":34,"2":35,"3":36,"4":37,"5":38,"6":39,"7":40,"8":41,"9":42,":":43,";":44,"<":45,"=":46,">":47,"?":48,"G":49,"H":50,"I":51,"P":52,"R":53,"T":54,"[":55,"]":56,"_":57,"a":58,"b":59,"c":60,"e":61,"f":62,"g":63,"h":64,"i":65,"l":66,"m":67,"n":68,"p":69,"r":70,"s":71,"t":72,"v":73,"x":74,"y":75,"|":76,"}":77,"~":78," ":79,"£":80,"§":81,"«":82,"±":83,"´":84,"·":85,"»":86,"×":87,"ˆ":88,"،":89,"؛":90,"؟":91,"ء":92,"آ":93,"أ":94,"ؤ":95,"إ":96,"ئ":97,"ا":98,"ب":99,"ة":100,"ت":101,"ث":102,"ج":103,"ح":104,"خ":105,"د":106,"ذ":107,"ر":108,"ز":109,"س":110,"ش":111,"ص":112,"ض":113,"ط":114,"ظ":115,"ع":116,"غ":117,"ف":118,"ق":119,"ك":120,"ل":121,"م":122,"ن":123,"ه":124,"و":125,"ى":126,"ي":127,"ً":128,"ٌ":129,"ٍ":130,"َ":131,"ُ":132,"ِ":133,"ّ":134,"ْ":135,"ٓ":136,"٤":137,"٩":138,"ٹ":139,"ک":140,"ی":141,"‌":142,"‍":143,"‏":144,"–":145,"“":146,"”":147,"„":148,"†":149,"…":150,"":151,"":152,"":153,"":154,"ﺑ":155,"�":156}
 
1
+ {"<|endoftext|>":0,"<|vsep|>":1,"<|bsep|>":2,"<|pad|>":3,"<|psep|>":4,"<|meter_0|>":5,"<|meter_1|>":6,"<|meter_2|>":7,"<|meter_3|>":8,"<|meter_4|>":9,"<|meter_5|>":10,"<|meter_6|>":11,"<|meter_7|>":12,"<|meter_8|>":13,"<|meter_9|>":14,"<|meter_10|>":15,"<|meter_11|>":16,"<|meter_12|>":17,"<|meter_13|>":18,"<|meter_14|>":19,"<|meter_15|>":20," ":21,"0":22,"1":23,"2":24,"3":25,"4":26,"5":27,"6":28,"7":29,"8":30,"9":31,"<":32,">":33,"_":34,"b":35,"e":36,"m":37,"p":38,"r":39,"s":40,"t":41,"v":42,"|":43,"~":44,"ء":45,"أ":46,"ؤ":47,"ئ":48,"ا":49,"ب":50,"ة":51,"ت":52,"ث":53,"ج":54,"ح":55,"خ":56,"د":57,"ذ":58,"ر":59,"ز":60,"س":61,"ش":62,"ص":63,"ض":64,"ط":65,"ظ":66,"ع":67,"غ":68,"ف":69,"ق":70,"ك":71,"ل":72,"م":73,"ن":74,"ه":75,"و":76,"ى":77,"ي":78,"ً":79,"ٌ":80,"ٍ":81,"َ":82,"ُ":83,"ِ":84,"ّ":85,"ْ":86}