Zaid commited on
Commit
5aa42fc
1 Parent(s): 201ce24

Upload tokenizer

Browse files
Files changed (5) hide show
  1. merges.txt +1 -0
  2. special_tokens_map.json +5 -0
  3. tokenizer.json +623 -0
  4. tokenizer_config.json +9 -0
  5. vocab.json +1 -0
merges.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ #version: 0.2
special_tokens_map.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "unk_token": "<|endoftext|>"
5
+ }
tokenizer.json ADDED
@@ -0,0 +1,623 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": null,
4
+ "padding": null,
5
+ "added_tokens": [
6
+ {
7
+ "id": 0,
8
+ "content": "<|endoftext|>",
9
+ "single_word": false,
10
+ "lstrip": false,
11
+ "rstrip": false,
12
+ "normalized": false,
13
+ "special": true
14
+ },
15
+ {
16
+ "id": 1,
17
+ "content": "<|psep|>",
18
+ "single_word": false,
19
+ "lstrip": false,
20
+ "rstrip": false,
21
+ "normalized": false,
22
+ "special": true
23
+ },
24
+ {
25
+ "id": 2,
26
+ "content": "</|psep|>",
27
+ "single_word": false,
28
+ "lstrip": false,
29
+ "rstrip": false,
30
+ "normalized": false,
31
+ "special": true
32
+ },
33
+ {
34
+ "id": 3,
35
+ "content": "<|vsep|>",
36
+ "single_word": false,
37
+ "lstrip": false,
38
+ "rstrip": false,
39
+ "normalized": false,
40
+ "special": true
41
+ },
42
+ {
43
+ "id": 4,
44
+ "content": "<|bsep|>",
45
+ "single_word": false,
46
+ "lstrip": false,
47
+ "rstrip": false,
48
+ "normalized": false,
49
+ "special": true
50
+ },
51
+ {
52
+ "id": 5,
53
+ "content": "</|bsep|>",
54
+ "single_word": false,
55
+ "lstrip": false,
56
+ "rstrip": false,
57
+ "normalized": false,
58
+ "special": true
59
+ },
60
+ {
61
+ "id": 6,
62
+ "content": "<|pad|>",
63
+ "single_word": false,
64
+ "lstrip": false,
65
+ "rstrip": false,
66
+ "normalized": false,
67
+ "special": true
68
+ },
69
+ {
70
+ "id": 7,
71
+ "content": "<|meter_0|>",
72
+ "single_word": false,
73
+ "lstrip": false,
74
+ "rstrip": false,
75
+ "normalized": false,
76
+ "special": true
77
+ },
78
+ {
79
+ "id": 8,
80
+ "content": "<|meter_1|>",
81
+ "single_word": false,
82
+ "lstrip": false,
83
+ "rstrip": false,
84
+ "normalized": false,
85
+ "special": true
86
+ },
87
+ {
88
+ "id": 9,
89
+ "content": "<|meter_2|>",
90
+ "single_word": false,
91
+ "lstrip": false,
92
+ "rstrip": false,
93
+ "normalized": false,
94
+ "special": true
95
+ },
96
+ {
97
+ "id": 10,
98
+ "content": "<|meter_3|>",
99
+ "single_word": false,
100
+ "lstrip": false,
101
+ "rstrip": false,
102
+ "normalized": false,
103
+ "special": true
104
+ },
105
+ {
106
+ "id": 11,
107
+ "content": "<|meter_4|>",
108
+ "single_word": false,
109
+ "lstrip": false,
110
+ "rstrip": false,
111
+ "normalized": false,
112
+ "special": true
113
+ },
114
+ {
115
+ "id": 12,
116
+ "content": "<|meter_5|>",
117
+ "single_word": false,
118
+ "lstrip": false,
119
+ "rstrip": false,
120
+ "normalized": false,
121
+ "special": true
122
+ },
123
+ {
124
+ "id": 13,
125
+ "content": "<|meter_6|>",
126
+ "single_word": false,
127
+ "lstrip": false,
128
+ "rstrip": false,
129
+ "normalized": false,
130
+ "special": true
131
+ },
132
+ {
133
+ "id": 14,
134
+ "content": "<|meter_7|>",
135
+ "single_word": false,
136
+ "lstrip": false,
137
+ "rstrip": false,
138
+ "normalized": false,
139
+ "special": true
140
+ },
141
+ {
142
+ "id": 15,
143
+ "content": "<|meter_8|>",
144
+ "single_word": false,
145
+ "lstrip": false,
146
+ "rstrip": false,
147
+ "normalized": false,
148
+ "special": true
149
+ },
150
+ {
151
+ "id": 16,
152
+ "content": "<|meter_9|>",
153
+ "single_word": false,
154
+ "lstrip": false,
155
+ "rstrip": false,
156
+ "normalized": false,
157
+ "special": true
158
+ },
159
+ {
160
+ "id": 17,
161
+ "content": "<|meter_10|>",
162
+ "single_word": false,
163
+ "lstrip": false,
164
+ "rstrip": false,
165
+ "normalized": false,
166
+ "special": true
167
+ },
168
+ {
169
+ "id": 18,
170
+ "content": "<|meter_11|>",
171
+ "single_word": false,
172
+ "lstrip": false,
173
+ "rstrip": false,
174
+ "normalized": false,
175
+ "special": true
176
+ },
177
+ {
178
+ "id": 19,
179
+ "content": "<|meter_12|>",
180
+ "single_word": false,
181
+ "lstrip": false,
182
+ "rstrip": false,
183
+ "normalized": false,
184
+ "special": true
185
+ },
186
+ {
187
+ "id": 20,
188
+ "content": "<|meter_13|>",
189
+ "single_word": false,
190
+ "lstrip": false,
191
+ "rstrip": false,
192
+ "normalized": false,
193
+ "special": true
194
+ },
195
+ {
196
+ "id": 21,
197
+ "content": "<|meter_14|>",
198
+ "single_word": false,
199
+ "lstrip": false,
200
+ "rstrip": false,
201
+ "normalized": false,
202
+ "special": true
203
+ },
204
+ {
205
+ "id": 22,
206
+ "content": "<|meter_15|>",
207
+ "single_word": false,
208
+ "lstrip": false,
209
+ "rstrip": false,
210
+ "normalized": false,
211
+ "special": true
212
+ },
213
+ {
214
+ "id": 23,
215
+ "content": "<|meter_16|>",
216
+ "single_word": false,
217
+ "lstrip": false,
218
+ "rstrip": false,
219
+ "normalized": false,
220
+ "special": true
221
+ },
222
+ {
223
+ "id": 24,
224
+ "content": "<|theme_0|>",
225
+ "single_word": false,
226
+ "lstrip": false,
227
+ "rstrip": false,
228
+ "normalized": false,
229
+ "special": true
230
+ },
231
+ {
232
+ "id": 25,
233
+ "content": "<|theme_1|>",
234
+ "single_word": false,
235
+ "lstrip": false,
236
+ "rstrip": false,
237
+ "normalized": false,
238
+ "special": true
239
+ },
240
+ {
241
+ "id": 26,
242
+ "content": "<|theme_2|>",
243
+ "single_word": false,
244
+ "lstrip": false,
245
+ "rstrip": false,
246
+ "normalized": false,
247
+ "special": true
248
+ },
249
+ {
250
+ "id": 27,
251
+ "content": "<|theme_3|>",
252
+ "single_word": false,
253
+ "lstrip": false,
254
+ "rstrip": false,
255
+ "normalized": false,
256
+ "special": true
257
+ },
258
+ {
259
+ "id": 28,
260
+ "content": "<|theme_4|>",
261
+ "single_word": false,
262
+ "lstrip": false,
263
+ "rstrip": false,
264
+ "normalized": false,
265
+ "special": true
266
+ },
267
+ {
268
+ "id": 29,
269
+ "content": "<|theme_5|>",
270
+ "single_word": false,
271
+ "lstrip": false,
272
+ "rstrip": false,
273
+ "normalized": false,
274
+ "special": true
275
+ },
276
+ {
277
+ "id": 30,
278
+ "content": "<|theme_6|>",
279
+ "single_word": false,
280
+ "lstrip": false,
281
+ "rstrip": false,
282
+ "normalized": false,
283
+ "special": true
284
+ },
285
+ {
286
+ "id": 31,
287
+ "content": "<|theme_7|>",
288
+ "single_word": false,
289
+ "lstrip": false,
290
+ "rstrip": false,
291
+ "normalized": false,
292
+ "special": true
293
+ },
294
+ {
295
+ "id": 32,
296
+ "content": "<|theme_8|>",
297
+ "single_word": false,
298
+ "lstrip": false,
299
+ "rstrip": false,
300
+ "normalized": false,
301
+ "special": true
302
+ },
303
+ {
304
+ "id": 33,
305
+ "content": "<|theme_9|>",
306
+ "single_word": false,
307
+ "lstrip": false,
308
+ "rstrip": false,
309
+ "normalized": false,
310
+ "special": true
311
+ },
312
+ {
313
+ "id": 34,
314
+ "content": "<|theme_10|>",
315
+ "single_word": false,
316
+ "lstrip": false,
317
+ "rstrip": false,
318
+ "normalized": false,
319
+ "special": true
320
+ },
321
+ {
322
+ "id": 35,
323
+ "content": "<|theme_11|>",
324
+ "single_word": false,
325
+ "lstrip": false,
326
+ "rstrip": false,
327
+ "normalized": false,
328
+ "special": true
329
+ },
330
+ {
331
+ "id": 36,
332
+ "content": "<|theme_12|>",
333
+ "single_word": false,
334
+ "lstrip": false,
335
+ "rstrip": false,
336
+ "normalized": false,
337
+ "special": true
338
+ },
339
+ {
340
+ "id": 37,
341
+ "content": "<|theme_13|>",
342
+ "single_word": false,
343
+ "lstrip": false,
344
+ "rstrip": false,
345
+ "normalized": false,
346
+ "special": true
347
+ },
348
+ {
349
+ "id": 38,
350
+ "content": "<|theme_14|>",
351
+ "single_word": false,
352
+ "lstrip": false,
353
+ "rstrip": false,
354
+ "normalized": false,
355
+ "special": true
356
+ },
357
+ {
358
+ "id": 39,
359
+ "content": "<|theme_15|>",
360
+ "single_word": false,
361
+ "lstrip": false,
362
+ "rstrip": false,
363
+ "normalized": false,
364
+ "special": true
365
+ },
366
+ {
367
+ "id": 40,
368
+ "content": "<|theme_16|>",
369
+ "single_word": false,
370
+ "lstrip": false,
371
+ "rstrip": false,
372
+ "normalized": false,
373
+ "special": true
374
+ },
375
+ {
376
+ "id": 41,
377
+ "content": "<|theme_17|>",
378
+ "single_word": false,
379
+ "lstrip": false,
380
+ "rstrip": false,
381
+ "normalized": false,
382
+ "special": true
383
+ },
384
+ {
385
+ "id": 42,
386
+ "content": "<|theme_18|>",
387
+ "single_word": false,
388
+ "lstrip": false,
389
+ "rstrip": false,
390
+ "normalized": false,
391
+ "special": true
392
+ },
393
+ {
394
+ "id": 43,
395
+ "content": "<|res_0|>",
396
+ "single_word": false,
397
+ "lstrip": false,
398
+ "rstrip": false,
399
+ "normalized": false,
400
+ "special": true
401
+ },
402
+ {
403
+ "id": 44,
404
+ "content": "<|res_1|>",
405
+ "single_word": false,
406
+ "lstrip": false,
407
+ "rstrip": false,
408
+ "normalized": false,
409
+ "special": true
410
+ },
411
+ {
412
+ "id": 45,
413
+ "content": "<|res_2|>",
414
+ "single_word": false,
415
+ "lstrip": false,
416
+ "rstrip": false,
417
+ "normalized": false,
418
+ "special": true
419
+ },
420
+ {
421
+ "id": 46,
422
+ "content": "<|res_3|>",
423
+ "single_word": false,
424
+ "lstrip": false,
425
+ "rstrip": false,
426
+ "normalized": false,
427
+ "special": true
428
+ },
429
+ {
430
+ "id": 47,
431
+ "content": "<|res_4|>",
432
+ "single_word": false,
433
+ "lstrip": false,
434
+ "rstrip": false,
435
+ "normalized": false,
436
+ "special": true
437
+ },
438
+ {
439
+ "id": 48,
440
+ "content": "<|res_5|>",
441
+ "single_word": false,
442
+ "lstrip": false,
443
+ "rstrip": false,
444
+ "normalized": false,
445
+ "special": true
446
+ },
447
+ {
448
+ "id": 49,
449
+ "content": "<|res_6|>",
450
+ "single_word": false,
451
+ "lstrip": false,
452
+ "rstrip": false,
453
+ "normalized": false,
454
+ "special": true
455
+ },
456
+ {
457
+ "id": 50,
458
+ "content": "<|res_7|>",
459
+ "single_word": false,
460
+ "lstrip": false,
461
+ "rstrip": false,
462
+ "normalized": false,
463
+ "special": true
464
+ },
465
+ {
466
+ "id": 51,
467
+ "content": "<|res_8|>",
468
+ "single_word": false,
469
+ "lstrip": false,
470
+ "rstrip": false,
471
+ "normalized": false,
472
+ "special": true
473
+ },
474
+ {
475
+ "id": 52,
476
+ "content": "<|res_9|>",
477
+ "single_word": false,
478
+ "lstrip": false,
479
+ "rstrip": false,
480
+ "normalized": false,
481
+ "special": true
482
+ }
483
+ ],
484
+ "normalizer": null,
485
+ "pre_tokenizer": {
486
+ "type": "UnicodeScripts"
487
+ },
488
+ "post_processor": null,
489
+ "decoder": null,
490
+ "model": {
491
+ "type": "BPE",
492
+ "dropout": null,
493
+ "unk_token": null,
494
+ "continuing_subword_prefix": null,
495
+ "end_of_word_suffix": null,
496
+ "fuse_unk": false,
497
+ "byte_fallback": false,
498
+ "vocab": {
499
+ "<|endoftext|>": 0,
500
+ "<|psep|>": 1,
501
+ "</|psep|>": 2,
502
+ "<|vsep|>": 3,
503
+ "<|bsep|>": 4,
504
+ "</|bsep|>": 5,
505
+ "<|pad|>": 6,
506
+ "<|meter_0|>": 7,
507
+ "<|meter_1|>": 8,
508
+ "<|meter_2|>": 9,
509
+ "<|meter_3|>": 10,
510
+ "<|meter_4|>": 11,
511
+ "<|meter_5|>": 12,
512
+ "<|meter_6|>": 13,
513
+ "<|meter_7|>": 14,
514
+ "<|meter_8|>": 15,
515
+ "<|meter_9|>": 16,
516
+ "<|meter_10|>": 17,
517
+ "<|meter_11|>": 18,
518
+ "<|meter_12|>": 19,
519
+ "<|meter_13|>": 20,
520
+ "<|meter_14|>": 21,
521
+ "<|meter_15|>": 22,
522
+ "<|meter_16|>": 23,
523
+ "<|theme_0|>": 24,
524
+ "<|theme_1|>": 25,
525
+ "<|theme_2|>": 26,
526
+ "<|theme_3|>": 27,
527
+ "<|theme_4|>": 28,
528
+ "<|theme_5|>": 29,
529
+ "<|theme_6|>": 30,
530
+ "<|theme_7|>": 31,
531
+ "<|theme_8|>": 32,
532
+ "<|theme_9|>": 33,
533
+ "<|theme_10|>": 34,
534
+ "<|theme_11|>": 35,
535
+ "<|theme_12|>": 36,
536
+ "<|theme_13|>": 37,
537
+ "<|theme_14|>": 38,
538
+ "<|theme_15|>": 39,
539
+ "<|theme_16|>": 40,
540
+ "<|theme_17|>": 41,
541
+ "<|theme_18|>": 42,
542
+ "<|res_0|>": 43,
543
+ "<|res_1|>": 44,
544
+ "<|res_2|>": 45,
545
+ "<|res_3|>": 46,
546
+ "<|res_4|>": 47,
547
+ "<|res_5|>": 48,
548
+ "<|res_6|>": 49,
549
+ "<|res_7|>": 50,
550
+ "<|res_8|>": 51,
551
+ "<|res_9|>": 52,
552
+ " ": 53,
553
+ "/": 54,
554
+ "0": 55,
555
+ "1": 56,
556
+ "2": 57,
557
+ "3": 58,
558
+ "4": 59,
559
+ "5": 60,
560
+ "6": 61,
561
+ "7": 62,
562
+ "8": 63,
563
+ "9": 64,
564
+ "<": 65,
565
+ ">": 66,
566
+ "_": 67,
567
+ "b": 68,
568
+ "e": 69,
569
+ "h": 70,
570
+ "m": 71,
571
+ "p": 72,
572
+ "r": 73,
573
+ "s": 74,
574
+ "t": 75,
575
+ "v": 76,
576
+ "|": 77,
577
+ "~": 78,
578
+ "ء": 79,
579
+ "أ": 80,
580
+ "ؤ": 81,
581
+ "ئ": 82,
582
+ "ا": 83,
583
+ "ب": 84,
584
+ "ة": 85,
585
+ "ت": 86,
586
+ "ث": 87,
587
+ "ج": 88,
588
+ "ح": 89,
589
+ "خ": 90,
590
+ "د": 91,
591
+ "ذ": 92,
592
+ "ر": 93,
593
+ "ز": 94,
594
+ "س": 95,
595
+ "ش": 96,
596
+ "ص": 97,
597
+ "ض": 98,
598
+ "ط": 99,
599
+ "ظ": 100,
600
+ "ع": 101,
601
+ "غ": 102,
602
+ "ف": 103,
603
+ "ق": 104,
604
+ "ك": 105,
605
+ "ل": 106,
606
+ "م": 107,
607
+ "ن": 108,
608
+ "ه": 109,
609
+ "و": 110,
610
+ "ى": 111,
611
+ "ي": 112,
612
+ "ً": 113,
613
+ "ٌ": 114,
614
+ "ٍ": 115,
615
+ "َ": 116,
616
+ "ُ": 117,
617
+ "ِ": 118,
618
+ "ّ": 119,
619
+ "ْ": 120
620
+ },
621
+ "merges": []
622
+ }
623
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<|endoftext|>",
4
+ "clean_up_tokenization_spaces": true,
5
+ "eos_token": "<|endoftext|>",
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "tokenizer_class": "GPT2Tokenizer",
8
+ "unk_token": "<|endoftext|>"
9
+ }
vocab.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"<|endoftext|>":0,"<|psep|>":1,"</|psep|>":2,"<|vsep|>":3,"<|bsep|>":4,"</|bsep|>":5,"<|pad|>":6,"<|meter_0|>":7,"<|meter_1|>":8,"<|meter_2|>":9,"<|meter_3|>":10,"<|meter_4|>":11,"<|meter_5|>":12,"<|meter_6|>":13,"<|meter_7|>":14,"<|meter_8|>":15,"<|meter_9|>":16,"<|meter_10|>":17,"<|meter_11|>":18,"<|meter_12|>":19,"<|meter_13|>":20,"<|meter_14|>":21,"<|meter_15|>":22,"<|meter_16|>":23,"<|theme_0|>":24,"<|theme_1|>":25,"<|theme_2|>":26,"<|theme_3|>":27,"<|theme_4|>":28,"<|theme_5|>":29,"<|theme_6|>":30,"<|theme_7|>":31,"<|theme_8|>":32,"<|theme_9|>":33,"<|theme_10|>":34,"<|theme_11|>":35,"<|theme_12|>":36,"<|theme_13|>":37,"<|theme_14|>":38,"<|theme_15|>":39,"<|theme_16|>":40,"<|theme_17|>":41,"<|theme_18|>":42,"<|res_0|>":43,"<|res_1|>":44,"<|res_2|>":45,"<|res_3|>":46,"<|res_4|>":47,"<|res_5|>":48,"<|res_6|>":49,"<|res_7|>":50,"<|res_8|>":51,"<|res_9|>":52," ":53,"/":54,"0":55,"1":56,"2":57,"3":58,"4":59,"5":60,"6":61,"7":62,"8":63,"9":64,"<":65,">":66,"_":67,"b":68,"e":69,"h":70,"m":71,"p":72,"r":73,"s":74,"t":75,"v":76,"|":77,"~":78,"ء":79,"أ":80,"ؤ":81,"ئ":82,"ا":83,"ب":84,"ة":85,"ت":86,"ث":87,"ج":88,"ح":89,"خ":90,"د":91,"ذ":92,"ر":93,"ز":94,"س":95,"ش":96,"ص":97,"ض":98,"ط":99,"ظ":100,"ع":101,"غ":102,"ف":103,"ق":104,"ك":105,"ل":106,"م":107,"ن":108,"ه":109,"و":110,"ى":111,"ي":112,"ً":113,"ٌ":114,"ٍ":115,"َ":116,"ُ":117,"ِ":118,"ّ":119,"ْ":120}