fabikru commited on
Commit
7bcfe99
·
verified ·
1 Parent(s): 097b488

Upload tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +37 -0
  2. tokenizer.json +855 -0
  3. tokenizer_config.json +661 -0
special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
tokenizer.json ADDED
@@ -0,0 +1,855 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": {
4
+ "direction": "Right",
5
+ "max_length": 500,
6
+ "strategy": "LongestFirst",
7
+ "stride": 0
8
+ },
9
+ "padding": null,
10
+ "added_tokens": [
11
+ {
12
+ "id": 0,
13
+ "content": "[UNK]",
14
+ "single_word": false,
15
+ "lstrip": false,
16
+ "rstrip": false,
17
+ "normalized": false,
18
+ "special": true
19
+ },
20
+ {
21
+ "id": 1,
22
+ "content": "[PAD]",
23
+ "single_word": false,
24
+ "lstrip": false,
25
+ "rstrip": false,
26
+ "normalized": false,
27
+ "special": true
28
+ },
29
+ {
30
+ "id": 2,
31
+ "content": "[CLS]",
32
+ "single_word": false,
33
+ "lstrip": false,
34
+ "rstrip": false,
35
+ "normalized": false,
36
+ "special": true
37
+ },
38
+ {
39
+ "id": 3,
40
+ "content": "[SEP]",
41
+ "single_word": false,
42
+ "lstrip": false,
43
+ "rstrip": false,
44
+ "normalized": false,
45
+ "special": true
46
+ },
47
+ {
48
+ "id": 4,
49
+ "content": "[MASK]",
50
+ "single_word": false,
51
+ "lstrip": false,
52
+ "rstrip": false,
53
+ "normalized": false,
54
+ "special": true
55
+ },
56
+ {
57
+ "id": 6,
58
+ "content": "A",
59
+ "single_word": false,
60
+ "lstrip": false,
61
+ "rstrip": false,
62
+ "normalized": true,
63
+ "special": false
64
+ },
65
+ {
66
+ "id": 7,
67
+ "content": "B",
68
+ "single_word": false,
69
+ "lstrip": false,
70
+ "rstrip": false,
71
+ "normalized": true,
72
+ "special": false
73
+ },
74
+ {
75
+ "id": 8,
76
+ "content": "C",
77
+ "single_word": false,
78
+ "lstrip": false,
79
+ "rstrip": false,
80
+ "normalized": true,
81
+ "special": false
82
+ },
83
+ {
84
+ "id": 9,
85
+ "content": "D",
86
+ "single_word": false,
87
+ "lstrip": false,
88
+ "rstrip": false,
89
+ "normalized": true,
90
+ "special": false
91
+ },
92
+ {
93
+ "id": 10,
94
+ "content": "E",
95
+ "single_word": false,
96
+ "lstrip": false,
97
+ "rstrip": false,
98
+ "normalized": true,
99
+ "special": false
100
+ },
101
+ {
102
+ "id": 11,
103
+ "content": "F",
104
+ "single_word": false,
105
+ "lstrip": false,
106
+ "rstrip": false,
107
+ "normalized": true,
108
+ "special": false
109
+ },
110
+ {
111
+ "id": 12,
112
+ "content": "G",
113
+ "single_word": false,
114
+ "lstrip": false,
115
+ "rstrip": false,
116
+ "normalized": true,
117
+ "special": false
118
+ },
119
+ {
120
+ "id": 13,
121
+ "content": "H",
122
+ "single_word": false,
123
+ "lstrip": false,
124
+ "rstrip": false,
125
+ "normalized": true,
126
+ "special": false
127
+ },
128
+ {
129
+ "id": 14,
130
+ "content": "I",
131
+ "single_word": false,
132
+ "lstrip": false,
133
+ "rstrip": false,
134
+ "normalized": true,
135
+ "special": false
136
+ },
137
+ {
138
+ "id": 15,
139
+ "content": "J",
140
+ "single_word": false,
141
+ "lstrip": false,
142
+ "rstrip": false,
143
+ "normalized": true,
144
+ "special": false
145
+ },
146
+ {
147
+ "id": 16,
148
+ "content": "K",
149
+ "single_word": false,
150
+ "lstrip": false,
151
+ "rstrip": false,
152
+ "normalized": true,
153
+ "special": false
154
+ },
155
+ {
156
+ "id": 17,
157
+ "content": "L",
158
+ "single_word": false,
159
+ "lstrip": false,
160
+ "rstrip": false,
161
+ "normalized": true,
162
+ "special": false
163
+ },
164
+ {
165
+ "id": 18,
166
+ "content": "M",
167
+ "single_word": false,
168
+ "lstrip": false,
169
+ "rstrip": false,
170
+ "normalized": true,
171
+ "special": false
172
+ },
173
+ {
174
+ "id": 19,
175
+ "content": "N",
176
+ "single_word": false,
177
+ "lstrip": false,
178
+ "rstrip": false,
179
+ "normalized": true,
180
+ "special": false
181
+ },
182
+ {
183
+ "id": 20,
184
+ "content": "O",
185
+ "single_word": false,
186
+ "lstrip": false,
187
+ "rstrip": false,
188
+ "normalized": true,
189
+ "special": false
190
+ },
191
+ {
192
+ "id": 21,
193
+ "content": "P",
194
+ "single_word": false,
195
+ "lstrip": false,
196
+ "rstrip": false,
197
+ "normalized": true,
198
+ "special": false
199
+ },
200
+ {
201
+ "id": 22,
202
+ "content": "Q",
203
+ "single_word": false,
204
+ "lstrip": false,
205
+ "rstrip": false,
206
+ "normalized": true,
207
+ "special": false
208
+ },
209
+ {
210
+ "id": 23,
211
+ "content": "R",
212
+ "single_word": false,
213
+ "lstrip": false,
214
+ "rstrip": false,
215
+ "normalized": true,
216
+ "special": false
217
+ },
218
+ {
219
+ "id": 24,
220
+ "content": "S",
221
+ "single_word": false,
222
+ "lstrip": false,
223
+ "rstrip": false,
224
+ "normalized": true,
225
+ "special": false
226
+ },
227
+ {
228
+ "id": 25,
229
+ "content": "T",
230
+ "single_word": false,
231
+ "lstrip": false,
232
+ "rstrip": false,
233
+ "normalized": true,
234
+ "special": false
235
+ },
236
+ {
237
+ "id": 26,
238
+ "content": "U",
239
+ "single_word": false,
240
+ "lstrip": false,
241
+ "rstrip": false,
242
+ "normalized": true,
243
+ "special": false
244
+ },
245
+ {
246
+ "id": 27,
247
+ "content": "V",
248
+ "single_word": false,
249
+ "lstrip": false,
250
+ "rstrip": false,
251
+ "normalized": true,
252
+ "special": false
253
+ },
254
+ {
255
+ "id": 28,
256
+ "content": "W",
257
+ "single_word": false,
258
+ "lstrip": false,
259
+ "rstrip": false,
260
+ "normalized": true,
261
+ "special": false
262
+ },
263
+ {
264
+ "id": 29,
265
+ "content": "X",
266
+ "single_word": false,
267
+ "lstrip": false,
268
+ "rstrip": false,
269
+ "normalized": true,
270
+ "special": false
271
+ },
272
+ {
273
+ "id": 30,
274
+ "content": "Y",
275
+ "single_word": false,
276
+ "lstrip": false,
277
+ "rstrip": false,
278
+ "normalized": true,
279
+ "special": false
280
+ },
281
+ {
282
+ "id": 31,
283
+ "content": "Z",
284
+ "single_word": false,
285
+ "lstrip": false,
286
+ "rstrip": false,
287
+ "normalized": true,
288
+ "special": false
289
+ },
290
+ {
291
+ "id": 32,
292
+ "content": "a",
293
+ "single_word": false,
294
+ "lstrip": false,
295
+ "rstrip": false,
296
+ "normalized": true,
297
+ "special": false
298
+ },
299
+ {
300
+ "id": 33,
301
+ "content": "b",
302
+ "single_word": false,
303
+ "lstrip": false,
304
+ "rstrip": false,
305
+ "normalized": true,
306
+ "special": false
307
+ },
308
+ {
309
+ "id": 34,
310
+ "content": "c",
311
+ "single_word": false,
312
+ "lstrip": false,
313
+ "rstrip": false,
314
+ "normalized": true,
315
+ "special": false
316
+ },
317
+ {
318
+ "id": 35,
319
+ "content": "d",
320
+ "single_word": false,
321
+ "lstrip": false,
322
+ "rstrip": false,
323
+ "normalized": true,
324
+ "special": false
325
+ },
326
+ {
327
+ "id": 36,
328
+ "content": "e",
329
+ "single_word": false,
330
+ "lstrip": false,
331
+ "rstrip": false,
332
+ "normalized": true,
333
+ "special": false
334
+ },
335
+ {
336
+ "id": 37,
337
+ "content": "f",
338
+ "single_word": false,
339
+ "lstrip": false,
340
+ "rstrip": false,
341
+ "normalized": true,
342
+ "special": false
343
+ },
344
+ {
345
+ "id": 38,
346
+ "content": "g",
347
+ "single_word": false,
348
+ "lstrip": false,
349
+ "rstrip": false,
350
+ "normalized": true,
351
+ "special": false
352
+ },
353
+ {
354
+ "id": 39,
355
+ "content": "h",
356
+ "single_word": false,
357
+ "lstrip": false,
358
+ "rstrip": false,
359
+ "normalized": true,
360
+ "special": false
361
+ },
362
+ {
363
+ "id": 40,
364
+ "content": "i",
365
+ "single_word": false,
366
+ "lstrip": false,
367
+ "rstrip": false,
368
+ "normalized": true,
369
+ "special": false
370
+ },
371
+ {
372
+ "id": 41,
373
+ "content": "j",
374
+ "single_word": false,
375
+ "lstrip": false,
376
+ "rstrip": false,
377
+ "normalized": true,
378
+ "special": false
379
+ },
380
+ {
381
+ "id": 42,
382
+ "content": "k",
383
+ "single_word": false,
384
+ "lstrip": false,
385
+ "rstrip": false,
386
+ "normalized": true,
387
+ "special": false
388
+ },
389
+ {
390
+ "id": 43,
391
+ "content": "l",
392
+ "single_word": false,
393
+ "lstrip": false,
394
+ "rstrip": false,
395
+ "normalized": true,
396
+ "special": false
397
+ },
398
+ {
399
+ "id": 44,
400
+ "content": "m",
401
+ "single_word": false,
402
+ "lstrip": false,
403
+ "rstrip": false,
404
+ "normalized": true,
405
+ "special": false
406
+ },
407
+ {
408
+ "id": 45,
409
+ "content": "n",
410
+ "single_word": false,
411
+ "lstrip": false,
412
+ "rstrip": false,
413
+ "normalized": true,
414
+ "special": false
415
+ },
416
+ {
417
+ "id": 46,
418
+ "content": "o",
419
+ "single_word": false,
420
+ "lstrip": false,
421
+ "rstrip": false,
422
+ "normalized": true,
423
+ "special": false
424
+ },
425
+ {
426
+ "id": 47,
427
+ "content": "p",
428
+ "single_word": false,
429
+ "lstrip": false,
430
+ "rstrip": false,
431
+ "normalized": true,
432
+ "special": false
433
+ },
434
+ {
435
+ "id": 48,
436
+ "content": "q",
437
+ "single_word": false,
438
+ "lstrip": false,
439
+ "rstrip": false,
440
+ "normalized": true,
441
+ "special": false
442
+ },
443
+ {
444
+ "id": 49,
445
+ "content": "r",
446
+ "single_word": false,
447
+ "lstrip": false,
448
+ "rstrip": false,
449
+ "normalized": true,
450
+ "special": false
451
+ },
452
+ {
453
+ "id": 50,
454
+ "content": "s",
455
+ "single_word": false,
456
+ "lstrip": false,
457
+ "rstrip": false,
458
+ "normalized": true,
459
+ "special": false
460
+ },
461
+ {
462
+ "id": 51,
463
+ "content": "t",
464
+ "single_word": false,
465
+ "lstrip": false,
466
+ "rstrip": false,
467
+ "normalized": true,
468
+ "special": false
469
+ },
470
+ {
471
+ "id": 52,
472
+ "content": "u",
473
+ "single_word": false,
474
+ "lstrip": false,
475
+ "rstrip": false,
476
+ "normalized": true,
477
+ "special": false
478
+ },
479
+ {
480
+ "id": 53,
481
+ "content": "v",
482
+ "single_word": false,
483
+ "lstrip": false,
484
+ "rstrip": false,
485
+ "normalized": true,
486
+ "special": false
487
+ },
488
+ {
489
+ "id": 54,
490
+ "content": "w",
491
+ "single_word": false,
492
+ "lstrip": false,
493
+ "rstrip": false,
494
+ "normalized": true,
495
+ "special": false
496
+ },
497
+ {
498
+ "id": 55,
499
+ "content": "x",
500
+ "single_word": false,
501
+ "lstrip": false,
502
+ "rstrip": false,
503
+ "normalized": true,
504
+ "special": false
505
+ },
506
+ {
507
+ "id": 56,
508
+ "content": "y",
509
+ "single_word": false,
510
+ "lstrip": false,
511
+ "rstrip": false,
512
+ "normalized": true,
513
+ "special": false
514
+ },
515
+ {
516
+ "id": 57,
517
+ "content": "z",
518
+ "single_word": false,
519
+ "lstrip": false,
520
+ "rstrip": false,
521
+ "normalized": true,
522
+ "special": false
523
+ },
524
+ {
525
+ "id": 58,
526
+ "content": "0",
527
+ "single_word": false,
528
+ "lstrip": false,
529
+ "rstrip": false,
530
+ "normalized": true,
531
+ "special": false
532
+ },
533
+ {
534
+ "id": 59,
535
+ "content": "1",
536
+ "single_word": false,
537
+ "lstrip": false,
538
+ "rstrip": false,
539
+ "normalized": true,
540
+ "special": false
541
+ },
542
+ {
543
+ "id": 60,
544
+ "content": "2",
545
+ "single_word": false,
546
+ "lstrip": false,
547
+ "rstrip": false,
548
+ "normalized": true,
549
+ "special": false
550
+ },
551
+ {
552
+ "id": 61,
553
+ "content": "3",
554
+ "single_word": false,
555
+ "lstrip": false,
556
+ "rstrip": false,
557
+ "normalized": true,
558
+ "special": false
559
+ },
560
+ {
561
+ "id": 62,
562
+ "content": "4",
563
+ "single_word": false,
564
+ "lstrip": false,
565
+ "rstrip": false,
566
+ "normalized": true,
567
+ "special": false
568
+ },
569
+ {
570
+ "id": 63,
571
+ "content": "5",
572
+ "single_word": false,
573
+ "lstrip": false,
574
+ "rstrip": false,
575
+ "normalized": true,
576
+ "special": false
577
+ },
578
+ {
579
+ "id": 64,
580
+ "content": "6",
581
+ "single_word": false,
582
+ "lstrip": false,
583
+ "rstrip": false,
584
+ "normalized": true,
585
+ "special": false
586
+ },
587
+ {
588
+ "id": 65,
589
+ "content": "7",
590
+ "single_word": false,
591
+ "lstrip": false,
592
+ "rstrip": false,
593
+ "normalized": true,
594
+ "special": false
595
+ },
596
+ {
597
+ "id": 66,
598
+ "content": "8",
599
+ "single_word": false,
600
+ "lstrip": false,
601
+ "rstrip": false,
602
+ "normalized": true,
603
+ "special": false
604
+ },
605
+ {
606
+ "id": 67,
607
+ "content": "9",
608
+ "single_word": false,
609
+ "lstrip": false,
610
+ "rstrip": false,
611
+ "normalized": true,
612
+ "special": false
613
+ },
614
+ {
615
+ "id": 68,
616
+ "content": "=",
617
+ "single_word": false,
618
+ "lstrip": false,
619
+ "rstrip": false,
620
+ "normalized": true,
621
+ "special": false
622
+ },
623
+ {
624
+ "id": 69,
625
+ "content": "#",
626
+ "single_word": false,
627
+ "lstrip": false,
628
+ "rstrip": false,
629
+ "normalized": true,
630
+ "special": false
631
+ },
632
+ {
633
+ "id": 70,
634
+ "content": ":",
635
+ "single_word": false,
636
+ "lstrip": false,
637
+ "rstrip": false,
638
+ "normalized": true,
639
+ "special": false
640
+ },
641
+ {
642
+ "id": 71,
643
+ "content": "+",
644
+ "single_word": false,
645
+ "lstrip": false,
646
+ "rstrip": false,
647
+ "normalized": true,
648
+ "special": false
649
+ },
650
+ {
651
+ "id": 72,
652
+ "content": "-",
653
+ "single_word": false,
654
+ "lstrip": false,
655
+ "rstrip": false,
656
+ "normalized": true,
657
+ "special": false
658
+ },
659
+ {
660
+ "id": 73,
661
+ "content": "[",
662
+ "single_word": false,
663
+ "lstrip": false,
664
+ "rstrip": false,
665
+ "normalized": true,
666
+ "special": false
667
+ },
668
+ {
669
+ "id": 74,
670
+ "content": "]",
671
+ "single_word": false,
672
+ "lstrip": false,
673
+ "rstrip": false,
674
+ "normalized": true,
675
+ "special": false
676
+ },
677
+ {
678
+ "id": 75,
679
+ "content": "(",
680
+ "single_word": false,
681
+ "lstrip": false,
682
+ "rstrip": false,
683
+ "normalized": true,
684
+ "special": false
685
+ },
686
+ {
687
+ "id": 76,
688
+ "content": ")",
689
+ "single_word": false,
690
+ "lstrip": false,
691
+ "rstrip": false,
692
+ "normalized": true,
693
+ "special": false
694
+ },
695
+ {
696
+ "id": 77,
697
+ "content": "/",
698
+ "single_word": false,
699
+ "lstrip": false,
700
+ "rstrip": false,
701
+ "normalized": true,
702
+ "special": false
703
+ },
704
+ {
705
+ "id": 78,
706
+ "content": "\\",
707
+ "single_word": false,
708
+ "lstrip": false,
709
+ "rstrip": false,
710
+ "normalized": true,
711
+ "special": false
712
+ },
713
+ {
714
+ "id": 79,
715
+ "content": "@",
716
+ "single_word": false,
717
+ "lstrip": false,
718
+ "rstrip": false,
719
+ "normalized": true,
720
+ "special": false
721
+ },
722
+ {
723
+ "id": 80,
724
+ "content": ".",
725
+ "single_word": false,
726
+ "lstrip": false,
727
+ "rstrip": false,
728
+ "normalized": true,
729
+ "special": false
730
+ },
731
+ {
732
+ "id": 81,
733
+ "content": "%",
734
+ "single_word": false,
735
+ "lstrip": false,
736
+ "rstrip": false,
737
+ "normalized": true,
738
+ "special": false
739
+ }
740
+ ],
741
+ "normalizer": {
742
+ "type": "Sequence",
743
+ "normalizers": [
744
+ {
745
+ "type": "NFD"
746
+ },
747
+ {
748
+ "type": "Strip",
749
+ "strip_left": true,
750
+ "strip_right": true
751
+ }
752
+ ]
753
+ },
754
+ "pre_tokenizer": {
755
+ "type": "Split",
756
+ "pattern": {
757
+ "Regex": "A-Za-z0-9=#:+\\-\\[\\]()/\\\\@.%"
758
+ },
759
+ "behavior": "Isolated",
760
+ "invert": false
761
+ },
762
+ "post_processor": {
763
+ "type": "TemplateProcessing",
764
+ "single": [
765
+ {
766
+ "SpecialToken": {
767
+ "id": "[CLS]",
768
+ "type_id": 0
769
+ }
770
+ },
771
+ {
772
+ "Sequence": {
773
+ "id": "A",
774
+ "type_id": 0
775
+ }
776
+ },
777
+ {
778
+ "SpecialToken": {
779
+ "id": "[SEP]",
780
+ "type_id": 0
781
+ }
782
+ }
783
+ ],
784
+ "pair": [
785
+ {
786
+ "SpecialToken": {
787
+ "id": "[CLS]",
788
+ "type_id": 0
789
+ }
790
+ },
791
+ {
792
+ "Sequence": {
793
+ "id": "A",
794
+ "type_id": 0
795
+ }
796
+ },
797
+ {
798
+ "SpecialToken": {
799
+ "id": "[SEP]",
800
+ "type_id": 0
801
+ }
802
+ },
803
+ {
804
+ "Sequence": {
805
+ "id": "B",
806
+ "type_id": 1
807
+ }
808
+ },
809
+ {
810
+ "SpecialToken": {
811
+ "id": "[SEP]",
812
+ "type_id": 1
813
+ }
814
+ }
815
+ ],
816
+ "special_tokens": {
817
+ "[CLS]": {
818
+ "id": "[CLS]",
819
+ "ids": [
820
+ 2
821
+ ],
822
+ "tokens": [
823
+ "[CLS]"
824
+ ]
825
+ },
826
+ "[SEP]": {
827
+ "id": "[SEP]",
828
+ "ids": [
829
+ 3
830
+ ],
831
+ "tokens": [
832
+ "[SEP]"
833
+ ]
834
+ }
835
+ }
836
+ },
837
+ "decoder": {
838
+ "type": "Strip",
839
+ "content": " ",
840
+ "start": 0,
841
+ "stop": 0
842
+ },
843
+ "model": {
844
+ "type": "WordLevel",
845
+ "vocab": {
846
+ "[UNK]": 0,
847
+ "[PAD]": 1,
848
+ "[CLS]": 2,
849
+ "[SEP]": 3,
850
+ "[MASK]": 4,
851
+ "CC": 5
852
+ },
853
+ "unk_token": "[UNK]"
854
+ }
855
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,661 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[UNK]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "[PAD]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "6": {
44
+ "content": "A",
45
+ "lstrip": false,
46
+ "normalized": true,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": false
50
+ },
51
+ "7": {
52
+ "content": "B",
53
+ "lstrip": false,
54
+ "normalized": true,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": false
58
+ },
59
+ "8": {
60
+ "content": "C",
61
+ "lstrip": false,
62
+ "normalized": true,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": false
66
+ },
67
+ "9": {
68
+ "content": "D",
69
+ "lstrip": false,
70
+ "normalized": true,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": false
74
+ },
75
+ "10": {
76
+ "content": "E",
77
+ "lstrip": false,
78
+ "normalized": true,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": false
82
+ },
83
+ "11": {
84
+ "content": "F",
85
+ "lstrip": false,
86
+ "normalized": true,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": false
90
+ },
91
+ "12": {
92
+ "content": "G",
93
+ "lstrip": false,
94
+ "normalized": true,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": false
98
+ },
99
+ "13": {
100
+ "content": "H",
101
+ "lstrip": false,
102
+ "normalized": true,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": false
106
+ },
107
+ "14": {
108
+ "content": "I",
109
+ "lstrip": false,
110
+ "normalized": true,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": false
114
+ },
115
+ "15": {
116
+ "content": "J",
117
+ "lstrip": false,
118
+ "normalized": true,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": false
122
+ },
123
+ "16": {
124
+ "content": "K",
125
+ "lstrip": false,
126
+ "normalized": true,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": false
130
+ },
131
+ "17": {
132
+ "content": "L",
133
+ "lstrip": false,
134
+ "normalized": true,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": false
138
+ },
139
+ "18": {
140
+ "content": "M",
141
+ "lstrip": false,
142
+ "normalized": true,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": false
146
+ },
147
+ "19": {
148
+ "content": "N",
149
+ "lstrip": false,
150
+ "normalized": true,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": false
154
+ },
155
+ "20": {
156
+ "content": "O",
157
+ "lstrip": false,
158
+ "normalized": true,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": false
162
+ },
163
+ "21": {
164
+ "content": "P",
165
+ "lstrip": false,
166
+ "normalized": true,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": false
170
+ },
171
+ "22": {
172
+ "content": "Q",
173
+ "lstrip": false,
174
+ "normalized": true,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": false
178
+ },
179
+ "23": {
180
+ "content": "R",
181
+ "lstrip": false,
182
+ "normalized": true,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": false
186
+ },
187
+ "24": {
188
+ "content": "S",
189
+ "lstrip": false,
190
+ "normalized": true,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": false
194
+ },
195
+ "25": {
196
+ "content": "T",
197
+ "lstrip": false,
198
+ "normalized": true,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": false
202
+ },
203
+ "26": {
204
+ "content": "U",
205
+ "lstrip": false,
206
+ "normalized": true,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": false
210
+ },
211
+ "27": {
212
+ "content": "V",
213
+ "lstrip": false,
214
+ "normalized": true,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": false
218
+ },
219
+ "28": {
220
+ "content": "W",
221
+ "lstrip": false,
222
+ "normalized": true,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": false
226
+ },
227
+ "29": {
228
+ "content": "X",
229
+ "lstrip": false,
230
+ "normalized": true,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": false
234
+ },
235
+ "30": {
236
+ "content": "Y",
237
+ "lstrip": false,
238
+ "normalized": true,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": false
242
+ },
243
+ "31": {
244
+ "content": "Z",
245
+ "lstrip": false,
246
+ "normalized": true,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": false
250
+ },
251
+ "32": {
252
+ "content": "a",
253
+ "lstrip": false,
254
+ "normalized": true,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": false
258
+ },
259
+ "33": {
260
+ "content": "b",
261
+ "lstrip": false,
262
+ "normalized": true,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": false
266
+ },
267
+ "34": {
268
+ "content": "c",
269
+ "lstrip": false,
270
+ "normalized": true,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": false
274
+ },
275
+ "35": {
276
+ "content": "d",
277
+ "lstrip": false,
278
+ "normalized": true,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": false
282
+ },
283
+ "36": {
284
+ "content": "e",
285
+ "lstrip": false,
286
+ "normalized": true,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": false
290
+ },
291
+ "37": {
292
+ "content": "f",
293
+ "lstrip": false,
294
+ "normalized": true,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": false
298
+ },
299
+ "38": {
300
+ "content": "g",
301
+ "lstrip": false,
302
+ "normalized": true,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": false
306
+ },
307
+ "39": {
308
+ "content": "h",
309
+ "lstrip": false,
310
+ "normalized": true,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": false
314
+ },
315
+ "40": {
316
+ "content": "i",
317
+ "lstrip": false,
318
+ "normalized": true,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": false
322
+ },
323
+ "41": {
324
+ "content": "j",
325
+ "lstrip": false,
326
+ "normalized": true,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": false
330
+ },
331
+ "42": {
332
+ "content": "k",
333
+ "lstrip": false,
334
+ "normalized": true,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": false
338
+ },
339
+ "43": {
340
+ "content": "l",
341
+ "lstrip": false,
342
+ "normalized": true,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": false
346
+ },
347
+ "44": {
348
+ "content": "m",
349
+ "lstrip": false,
350
+ "normalized": true,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": false
354
+ },
355
+ "45": {
356
+ "content": "n",
357
+ "lstrip": false,
358
+ "normalized": true,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": false
362
+ },
363
+ "46": {
364
+ "content": "o",
365
+ "lstrip": false,
366
+ "normalized": true,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": false
370
+ },
371
+ "47": {
372
+ "content": "p",
373
+ "lstrip": false,
374
+ "normalized": true,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": false
378
+ },
379
+ "48": {
380
+ "content": "q",
381
+ "lstrip": false,
382
+ "normalized": true,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": false
386
+ },
387
+ "49": {
388
+ "content": "r",
389
+ "lstrip": false,
390
+ "normalized": true,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": false
394
+ },
395
+ "50": {
396
+ "content": "s",
397
+ "lstrip": false,
398
+ "normalized": true,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": false
402
+ },
403
+ "51": {
404
+ "content": "t",
405
+ "lstrip": false,
406
+ "normalized": true,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": false
410
+ },
411
+ "52": {
412
+ "content": "u",
413
+ "lstrip": false,
414
+ "normalized": true,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": false
418
+ },
419
+ "53": {
420
+ "content": "v",
421
+ "lstrip": false,
422
+ "normalized": true,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": false
426
+ },
427
+ "54": {
428
+ "content": "w",
429
+ "lstrip": false,
430
+ "normalized": true,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": false
434
+ },
435
+ "55": {
436
+ "content": "x",
437
+ "lstrip": false,
438
+ "normalized": true,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": false
442
+ },
443
+ "56": {
444
+ "content": "y",
445
+ "lstrip": false,
446
+ "normalized": true,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": false
450
+ },
451
+ "57": {
452
+ "content": "z",
453
+ "lstrip": false,
454
+ "normalized": true,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": false
458
+ },
459
+ "58": {
460
+ "content": "0",
461
+ "lstrip": false,
462
+ "normalized": true,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": false
466
+ },
467
+ "59": {
468
+ "content": "1",
469
+ "lstrip": false,
470
+ "normalized": true,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": false
474
+ },
475
+ "60": {
476
+ "content": "2",
477
+ "lstrip": false,
478
+ "normalized": true,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": false
482
+ },
483
+ "61": {
484
+ "content": "3",
485
+ "lstrip": false,
486
+ "normalized": true,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": false
490
+ },
491
+ "62": {
492
+ "content": "4",
493
+ "lstrip": false,
494
+ "normalized": true,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": false
498
+ },
499
+ "63": {
500
+ "content": "5",
501
+ "lstrip": false,
502
+ "normalized": true,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": false
506
+ },
507
+ "64": {
508
+ "content": "6",
509
+ "lstrip": false,
510
+ "normalized": true,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": false
514
+ },
515
+ "65": {
516
+ "content": "7",
517
+ "lstrip": false,
518
+ "normalized": true,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": false
522
+ },
523
+ "66": {
524
+ "content": "8",
525
+ "lstrip": false,
526
+ "normalized": true,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": false
530
+ },
531
+ "67": {
532
+ "content": "9",
533
+ "lstrip": false,
534
+ "normalized": true,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": false
538
+ },
539
+ "68": {
540
+ "content": "=",
541
+ "lstrip": false,
542
+ "normalized": true,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": false
546
+ },
547
+ "69": {
548
+ "content": "#",
549
+ "lstrip": false,
550
+ "normalized": true,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": false
554
+ },
555
+ "70": {
556
+ "content": ":",
557
+ "lstrip": false,
558
+ "normalized": true,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": false
562
+ },
563
+ "71": {
564
+ "content": "+",
565
+ "lstrip": false,
566
+ "normalized": true,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": false
570
+ },
571
+ "72": {
572
+ "content": "-",
573
+ "lstrip": false,
574
+ "normalized": true,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": false
578
+ },
579
+ "73": {
580
+ "content": "[",
581
+ "lstrip": false,
582
+ "normalized": true,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": false
586
+ },
587
+ "74": {
588
+ "content": "]",
589
+ "lstrip": false,
590
+ "normalized": true,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": false
594
+ },
595
+ "75": {
596
+ "content": "(",
597
+ "lstrip": false,
598
+ "normalized": true,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": false
602
+ },
603
+ "76": {
604
+ "content": ")",
605
+ "lstrip": false,
606
+ "normalized": true,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": false
610
+ },
611
+ "77": {
612
+ "content": "/",
613
+ "lstrip": false,
614
+ "normalized": true,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": false
618
+ },
619
+ "78": {
620
+ "content": "\\",
621
+ "lstrip": false,
622
+ "normalized": true,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": false
626
+ },
627
+ "79": {
628
+ "content": "@",
629
+ "lstrip": false,
630
+ "normalized": true,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": false
634
+ },
635
+ "80": {
636
+ "content": ".",
637
+ "lstrip": false,
638
+ "normalized": true,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": false
642
+ },
643
+ "81": {
644
+ "content": "%",
645
+ "lstrip": false,
646
+ "normalized": true,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": false
650
+ }
651
+ },
652
+ "clean_up_tokenization_spaces": false,
653
+ "cls_token": "[CLS]",
654
+ "extra_special_tokens": {},
655
+ "mask_token": "[MASK]",
656
+ "model_max_length": 1000000000000000019884624838656,
657
+ "pad_token": "[PAD]",
658
+ "sep_token": "[SEP]",
659
+ "tokenizer_class": "PreTrainedTokenizer",
660
+ "unk_token": "[UNK]"
661
+ }