Jingshu commited on
Commit
24df050
·
verified ·
1 Parent(s): 05f7eb2

Upload tokenizer

Browse files
Files changed (4) hide show
  1. special_tokens_map.json +1 -1
  2. tokenizer.json +0 -0
  3. tokenizer_config.json +18 -901
  4. vocab.txt +0 -0
special_tokens_map.json CHANGED
@@ -8,7 +8,7 @@
8
  },
9
  "mask_token": {
10
  "content": "[MASK]",
11
- "lstrip": true,
12
  "normalized": false,
13
  "rstrip": false,
14
  "single_word": false
 
8
  },
9
  "mask_token": {
10
  "content": "[MASK]",
11
+ "lstrip": false,
12
  "normalized": false,
13
  "rstrip": false,
14
  "single_word": false
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,231 +1,14 @@
1
  {
2
- "add_prefix_space": true,
3
  "added_tokens_decoder": {
4
  "0": {
5
- "content": "|||IP_ADDRESS|||",
6
- "lstrip": false,
7
- "normalized": true,
8
- "rstrip": false,
9
- "single_word": false,
10
- "special": false
11
- },
12
- "1": {
13
- "content": "<|padding|>",
14
- "lstrip": false,
15
- "normalized": false,
16
- "rstrip": false,
17
- "single_word": false,
18
- "special": true
19
- },
20
- "50254": {
21
- "content": " ",
22
- "lstrip": false,
23
- "normalized": true,
24
- "rstrip": false,
25
- "single_word": false,
26
- "special": false
27
- },
28
- "50255": {
29
- "content": " ",
30
- "lstrip": false,
31
- "normalized": true,
32
- "rstrip": false,
33
- "single_word": false,
34
- "special": false
35
- },
36
- "50256": {
37
- "content": " ",
38
- "lstrip": false,
39
- "normalized": true,
40
- "rstrip": false,
41
- "single_word": false,
42
- "special": false
43
- },
44
- "50257": {
45
- "content": " ",
46
- "lstrip": false,
47
- "normalized": true,
48
- "rstrip": false,
49
- "single_word": false,
50
- "special": false
51
- },
52
- "50258": {
53
- "content": " ",
54
- "lstrip": false,
55
- "normalized": true,
56
- "rstrip": false,
57
- "single_word": false,
58
- "special": false
59
- },
60
- "50259": {
61
- "content": " ",
62
- "lstrip": false,
63
- "normalized": true,
64
- "rstrip": false,
65
- "single_word": false,
66
- "special": false
67
- },
68
- "50260": {
69
- "content": " ",
70
- "lstrip": false,
71
- "normalized": true,
72
- "rstrip": false,
73
- "single_word": false,
74
- "special": false
75
- },
76
- "50261": {
77
- "content": " ",
78
- "lstrip": false,
79
- "normalized": true,
80
- "rstrip": false,
81
- "single_word": false,
82
- "special": false
83
- },
84
- "50262": {
85
- "content": " ",
86
- "lstrip": false,
87
- "normalized": true,
88
- "rstrip": false,
89
- "single_word": false,
90
- "special": false
91
- },
92
- "50263": {
93
- "content": " ",
94
- "lstrip": false,
95
- "normalized": true,
96
- "rstrip": false,
97
- "single_word": false,
98
- "special": false
99
- },
100
- "50264": {
101
- "content": " ",
102
- "lstrip": false,
103
- "normalized": true,
104
- "rstrip": false,
105
- "single_word": false,
106
- "special": false
107
- },
108
- "50265": {
109
- "content": " ",
110
- "lstrip": false,
111
- "normalized": true,
112
- "rstrip": false,
113
- "single_word": false,
114
- "special": false
115
- },
116
- "50266": {
117
- "content": " ",
118
- "lstrip": false,
119
- "normalized": true,
120
- "rstrip": false,
121
- "single_word": false,
122
- "special": false
123
- },
124
- "50267": {
125
- "content": " ",
126
- "lstrip": false,
127
- "normalized": true,
128
- "rstrip": false,
129
- "single_word": false,
130
- "special": false
131
- },
132
- "50268": {
133
- "content": " ",
134
- "lstrip": false,
135
- "normalized": true,
136
- "rstrip": false,
137
- "single_word": false,
138
- "special": false
139
- },
140
- "50269": {
141
- "content": " ",
142
- "lstrip": false,
143
- "normalized": true,
144
- "rstrip": false,
145
- "single_word": false,
146
- "special": false
147
- },
148
- "50270": {
149
- "content": " ",
150
- "lstrip": false,
151
- "normalized": true,
152
- "rstrip": false,
153
- "single_word": false,
154
- "special": false
155
- },
156
- "50271": {
157
- "content": " ",
158
- "lstrip": false,
159
- "normalized": true,
160
- "rstrip": false,
161
- "single_word": false,
162
- "special": false
163
- },
164
- "50272": {
165
- "content": " ",
166
- "lstrip": false,
167
- "normalized": true,
168
- "rstrip": false,
169
- "single_word": false,
170
- "special": false
171
- },
172
- "50273": {
173
- "content": " ",
174
- "lstrip": false,
175
- "normalized": true,
176
- "rstrip": false,
177
- "single_word": false,
178
- "special": false
179
- },
180
- "50274": {
181
- "content": " ",
182
- "lstrip": false,
183
- "normalized": true,
184
- "rstrip": false,
185
- "single_word": false,
186
- "special": false
187
- },
188
- "50275": {
189
- "content": " ",
190
- "lstrip": false,
191
- "normalized": true,
192
- "rstrip": false,
193
- "single_word": false,
194
- "special": false
195
- },
196
- "50276": {
197
- "content": " ",
198
- "lstrip": false,
199
- "normalized": true,
200
- "rstrip": false,
201
- "single_word": false,
202
- "special": false
203
- },
204
- "50277": {
205
- "content": "|||EMAIL_ADDRESS|||",
206
- "lstrip": false,
207
- "normalized": true,
208
- "rstrip": false,
209
- "single_word": false,
210
- "special": false
211
- },
212
- "50278": {
213
- "content": "|||PHONE_NUMBER|||",
214
- "lstrip": false,
215
- "normalized": true,
216
- "rstrip": false,
217
- "single_word": false,
218
- "special": false
219
- },
220
- "50279": {
221
- "content": "<|endoftext|>",
222
  "lstrip": false,
223
  "normalized": false,
224
  "rstrip": false,
225
  "single_word": false,
226
  "special": true
227
  },
228
- "50280": {
229
  "content": "[UNK]",
230
  "lstrip": false,
231
  "normalized": false,
@@ -233,7 +16,7 @@
233
  "single_word": false,
234
  "special": true
235
  },
236
- "50281": {
237
  "content": "[CLS]",
238
  "lstrip": false,
239
  "normalized": false,
@@ -241,7 +24,7 @@
241
  "single_word": false,
242
  "special": true
243
  },
244
- "50282": {
245
  "content": "[SEP]",
246
  "lstrip": false,
247
  "normalized": false,
@@ -249,698 +32,32 @@
249
  "single_word": false,
250
  "special": true
251
  },
252
- "50283": {
253
- "content": "[PAD]",
254
- "lstrip": false,
255
- "normalized": false,
256
- "rstrip": false,
257
- "single_word": false,
258
- "special": true
259
- },
260
- "50284": {
261
  "content": "[MASK]",
262
- "lstrip": true,
263
  "normalized": false,
264
  "rstrip": false,
265
  "single_word": false,
266
  "special": true
267
- },
268
- "50285": {
269
- "content": "[unused0]",
270
- "lstrip": false,
271
- "normalized": true,
272
- "rstrip": false,
273
- "single_word": false,
274
- "special": false
275
- },
276
- "50286": {
277
- "content": "[unused1]",
278
- "lstrip": false,
279
- "normalized": true,
280
- "rstrip": false,
281
- "single_word": false,
282
- "special": false
283
- },
284
- "50287": {
285
- "content": "[unused2]",
286
- "lstrip": false,
287
- "normalized": true,
288
- "rstrip": false,
289
- "single_word": false,
290
- "special": false
291
- },
292
- "50288": {
293
- "content": "[unused3]",
294
- "lstrip": false,
295
- "normalized": true,
296
- "rstrip": false,
297
- "single_word": false,
298
- "special": false
299
- },
300
- "50289": {
301
- "content": "[unused4]",
302
- "lstrip": false,
303
- "normalized": true,
304
- "rstrip": false,
305
- "single_word": false,
306
- "special": false
307
- },
308
- "50290": {
309
- "content": "[unused5]",
310
- "lstrip": false,
311
- "normalized": true,
312
- "rstrip": false,
313
- "single_word": false,
314
- "special": false
315
- },
316
- "50291": {
317
- "content": "[unused6]",
318
- "lstrip": false,
319
- "normalized": true,
320
- "rstrip": false,
321
- "single_word": false,
322
- "special": false
323
- },
324
- "50292": {
325
- "content": "[unused7]",
326
- "lstrip": false,
327
- "normalized": true,
328
- "rstrip": false,
329
- "single_word": false,
330
- "special": false
331
- },
332
- "50293": {
333
- "content": "[unused8]",
334
- "lstrip": false,
335
- "normalized": true,
336
- "rstrip": false,
337
- "single_word": false,
338
- "special": false
339
- },
340
- "50294": {
341
- "content": "[unused9]",
342
- "lstrip": false,
343
- "normalized": true,
344
- "rstrip": false,
345
- "single_word": false,
346
- "special": false
347
- },
348
- "50295": {
349
- "content": "[unused10]",
350
- "lstrip": false,
351
- "normalized": true,
352
- "rstrip": false,
353
- "single_word": false,
354
- "special": false
355
- },
356
- "50296": {
357
- "content": "[unused11]",
358
- "lstrip": false,
359
- "normalized": true,
360
- "rstrip": false,
361
- "single_word": false,
362
- "special": false
363
- },
364
- "50297": {
365
- "content": "[unused12]",
366
- "lstrip": false,
367
- "normalized": true,
368
- "rstrip": false,
369
- "single_word": false,
370
- "special": false
371
- },
372
- "50298": {
373
- "content": "[unused13]",
374
- "lstrip": false,
375
- "normalized": true,
376
- "rstrip": false,
377
- "single_word": false,
378
- "special": false
379
- },
380
- "50299": {
381
- "content": "[unused14]",
382
- "lstrip": false,
383
- "normalized": true,
384
- "rstrip": false,
385
- "single_word": false,
386
- "special": false
387
- },
388
- "50300": {
389
- "content": "[unused15]",
390
- "lstrip": false,
391
- "normalized": true,
392
- "rstrip": false,
393
- "single_word": false,
394
- "special": false
395
- },
396
- "50301": {
397
- "content": "[unused16]",
398
- "lstrip": false,
399
- "normalized": true,
400
- "rstrip": false,
401
- "single_word": false,
402
- "special": false
403
- },
404
- "50302": {
405
- "content": "[unused17]",
406
- "lstrip": false,
407
- "normalized": true,
408
- "rstrip": false,
409
- "single_word": false,
410
- "special": false
411
- },
412
- "50303": {
413
- "content": "[unused18]",
414
- "lstrip": false,
415
- "normalized": true,
416
- "rstrip": false,
417
- "single_word": false,
418
- "special": false
419
- },
420
- "50304": {
421
- "content": "[unused19]",
422
- "lstrip": false,
423
- "normalized": true,
424
- "rstrip": false,
425
- "single_word": false,
426
- "special": false
427
- },
428
- "50305": {
429
- "content": "[unused20]",
430
- "lstrip": false,
431
- "normalized": true,
432
- "rstrip": false,
433
- "single_word": false,
434
- "special": false
435
- },
436
- "50306": {
437
- "content": "[unused21]",
438
- "lstrip": false,
439
- "normalized": true,
440
- "rstrip": false,
441
- "single_word": false,
442
- "special": false
443
- },
444
- "50307": {
445
- "content": "[unused22]",
446
- "lstrip": false,
447
- "normalized": true,
448
- "rstrip": false,
449
- "single_word": false,
450
- "special": false
451
- },
452
- "50308": {
453
- "content": "[unused23]",
454
- "lstrip": false,
455
- "normalized": true,
456
- "rstrip": false,
457
- "single_word": false,
458
- "special": false
459
- },
460
- "50309": {
461
- "content": "[unused24]",
462
- "lstrip": false,
463
- "normalized": true,
464
- "rstrip": false,
465
- "single_word": false,
466
- "special": false
467
- },
468
- "50310": {
469
- "content": "[unused25]",
470
- "lstrip": false,
471
- "normalized": true,
472
- "rstrip": false,
473
- "single_word": false,
474
- "special": false
475
- },
476
- "50311": {
477
- "content": "[unused26]",
478
- "lstrip": false,
479
- "normalized": true,
480
- "rstrip": false,
481
- "single_word": false,
482
- "special": false
483
- },
484
- "50312": {
485
- "content": "[unused27]",
486
- "lstrip": false,
487
- "normalized": true,
488
- "rstrip": false,
489
- "single_word": false,
490
- "special": false
491
- },
492
- "50313": {
493
- "content": "[unused28]",
494
- "lstrip": false,
495
- "normalized": true,
496
- "rstrip": false,
497
- "single_word": false,
498
- "special": false
499
- },
500
- "50314": {
501
- "content": "[unused29]",
502
- "lstrip": false,
503
- "normalized": true,
504
- "rstrip": false,
505
- "single_word": false,
506
- "special": false
507
- },
508
- "50315": {
509
- "content": "[unused30]",
510
- "lstrip": false,
511
- "normalized": true,
512
- "rstrip": false,
513
- "single_word": false,
514
- "special": false
515
- },
516
- "50316": {
517
- "content": "[unused31]",
518
- "lstrip": false,
519
- "normalized": true,
520
- "rstrip": false,
521
- "single_word": false,
522
- "special": false
523
- },
524
- "50317": {
525
- "content": "[unused32]",
526
- "lstrip": false,
527
- "normalized": true,
528
- "rstrip": false,
529
- "single_word": false,
530
- "special": false
531
- },
532
- "50318": {
533
- "content": "[unused33]",
534
- "lstrip": false,
535
- "normalized": true,
536
- "rstrip": false,
537
- "single_word": false,
538
- "special": false
539
- },
540
- "50319": {
541
- "content": "[unused34]",
542
- "lstrip": false,
543
- "normalized": true,
544
- "rstrip": false,
545
- "single_word": false,
546
- "special": false
547
- },
548
- "50320": {
549
- "content": "[unused35]",
550
- "lstrip": false,
551
- "normalized": true,
552
- "rstrip": false,
553
- "single_word": false,
554
- "special": false
555
- },
556
- "50321": {
557
- "content": "[unused36]",
558
- "lstrip": false,
559
- "normalized": true,
560
- "rstrip": false,
561
- "single_word": false,
562
- "special": false
563
- },
564
- "50322": {
565
- "content": "[unused37]",
566
- "lstrip": false,
567
- "normalized": true,
568
- "rstrip": false,
569
- "single_word": false,
570
- "special": false
571
- },
572
- "50323": {
573
- "content": "[unused38]",
574
- "lstrip": false,
575
- "normalized": true,
576
- "rstrip": false,
577
- "single_word": false,
578
- "special": false
579
- },
580
- "50324": {
581
- "content": "[unused39]",
582
- "lstrip": false,
583
- "normalized": true,
584
- "rstrip": false,
585
- "single_word": false,
586
- "special": false
587
- },
588
- "50325": {
589
- "content": "[unused40]",
590
- "lstrip": false,
591
- "normalized": true,
592
- "rstrip": false,
593
- "single_word": false,
594
- "special": false
595
- },
596
- "50326": {
597
- "content": "[unused41]",
598
- "lstrip": false,
599
- "normalized": true,
600
- "rstrip": false,
601
- "single_word": false,
602
- "special": false
603
- },
604
- "50327": {
605
- "content": "[unused42]",
606
- "lstrip": false,
607
- "normalized": true,
608
- "rstrip": false,
609
- "single_word": false,
610
- "special": false
611
- },
612
- "50328": {
613
- "content": "[unused43]",
614
- "lstrip": false,
615
- "normalized": true,
616
- "rstrip": false,
617
- "single_word": false,
618
- "special": false
619
- },
620
- "50329": {
621
- "content": "[unused44]",
622
- "lstrip": false,
623
- "normalized": true,
624
- "rstrip": false,
625
- "single_word": false,
626
- "special": false
627
- },
628
- "50330": {
629
- "content": "[unused45]",
630
- "lstrip": false,
631
- "normalized": true,
632
- "rstrip": false,
633
- "single_word": false,
634
- "special": false
635
- },
636
- "50331": {
637
- "content": "[unused46]",
638
- "lstrip": false,
639
- "normalized": true,
640
- "rstrip": false,
641
- "single_word": false,
642
- "special": false
643
- },
644
- "50332": {
645
- "content": "[unused47]",
646
- "lstrip": false,
647
- "normalized": true,
648
- "rstrip": false,
649
- "single_word": false,
650
- "special": false
651
- },
652
- "50333": {
653
- "content": "[unused48]",
654
- "lstrip": false,
655
- "normalized": true,
656
- "rstrip": false,
657
- "single_word": false,
658
- "special": false
659
- },
660
- "50334": {
661
- "content": "[unused49]",
662
- "lstrip": false,
663
- "normalized": true,
664
- "rstrip": false,
665
- "single_word": false,
666
- "special": false
667
- },
668
- "50335": {
669
- "content": "[unused50]",
670
- "lstrip": false,
671
- "normalized": true,
672
- "rstrip": false,
673
- "single_word": false,
674
- "special": false
675
- },
676
- "50336": {
677
- "content": "[unused51]",
678
- "lstrip": false,
679
- "normalized": true,
680
- "rstrip": false,
681
- "single_word": false,
682
- "special": false
683
- },
684
- "50337": {
685
- "content": "[unused52]",
686
- "lstrip": false,
687
- "normalized": true,
688
- "rstrip": false,
689
- "single_word": false,
690
- "special": false
691
- },
692
- "50338": {
693
- "content": "[unused53]",
694
- "lstrip": false,
695
- "normalized": true,
696
- "rstrip": false,
697
- "single_word": false,
698
- "special": false
699
- },
700
- "50339": {
701
- "content": "[unused54]",
702
- "lstrip": false,
703
- "normalized": true,
704
- "rstrip": false,
705
- "single_word": false,
706
- "special": false
707
- },
708
- "50340": {
709
- "content": "[unused55]",
710
- "lstrip": false,
711
- "normalized": true,
712
- "rstrip": false,
713
- "single_word": false,
714
- "special": false
715
- },
716
- "50341": {
717
- "content": "[unused56]",
718
- "lstrip": false,
719
- "normalized": true,
720
- "rstrip": false,
721
- "single_word": false,
722
- "special": false
723
- },
724
- "50342": {
725
- "content": "[unused57]",
726
- "lstrip": false,
727
- "normalized": true,
728
- "rstrip": false,
729
- "single_word": false,
730
- "special": false
731
- },
732
- "50343": {
733
- "content": "[unused58]",
734
- "lstrip": false,
735
- "normalized": true,
736
- "rstrip": false,
737
- "single_word": false,
738
- "special": false
739
- },
740
- "50344": {
741
- "content": "[unused59]",
742
- "lstrip": false,
743
- "normalized": true,
744
- "rstrip": false,
745
- "single_word": false,
746
- "special": false
747
- },
748
- "50345": {
749
- "content": "[unused60]",
750
- "lstrip": false,
751
- "normalized": true,
752
- "rstrip": false,
753
- "single_word": false,
754
- "special": false
755
- },
756
- "50346": {
757
- "content": "[unused61]",
758
- "lstrip": false,
759
- "normalized": true,
760
- "rstrip": false,
761
- "single_word": false,
762
- "special": false
763
- },
764
- "50347": {
765
- "content": "[unused62]",
766
- "lstrip": false,
767
- "normalized": true,
768
- "rstrip": false,
769
- "single_word": false,
770
- "special": false
771
- },
772
- "50348": {
773
- "content": "[unused63]",
774
- "lstrip": false,
775
- "normalized": true,
776
- "rstrip": false,
777
- "single_word": false,
778
- "special": false
779
- },
780
- "50349": {
781
- "content": "[unused64]",
782
- "lstrip": false,
783
- "normalized": true,
784
- "rstrip": false,
785
- "single_word": false,
786
- "special": false
787
- },
788
- "50350": {
789
- "content": "[unused65]",
790
- "lstrip": false,
791
- "normalized": true,
792
- "rstrip": false,
793
- "single_word": false,
794
- "special": false
795
- },
796
- "50351": {
797
- "content": "[unused66]",
798
- "lstrip": false,
799
- "normalized": true,
800
- "rstrip": false,
801
- "single_word": false,
802
- "special": false
803
- },
804
- "50352": {
805
- "content": "[unused67]",
806
- "lstrip": false,
807
- "normalized": true,
808
- "rstrip": false,
809
- "single_word": false,
810
- "special": false
811
- },
812
- "50353": {
813
- "content": "[unused68]",
814
- "lstrip": false,
815
- "normalized": true,
816
- "rstrip": false,
817
- "single_word": false,
818
- "special": false
819
- },
820
- "50354": {
821
- "content": "[unused69]",
822
- "lstrip": false,
823
- "normalized": true,
824
- "rstrip": false,
825
- "single_word": false,
826
- "special": false
827
- },
828
- "50355": {
829
- "content": "[unused70]",
830
- "lstrip": false,
831
- "normalized": true,
832
- "rstrip": false,
833
- "single_word": false,
834
- "special": false
835
- },
836
- "50356": {
837
- "content": "[unused71]",
838
- "lstrip": false,
839
- "normalized": true,
840
- "rstrip": false,
841
- "single_word": false,
842
- "special": false
843
- },
844
- "50357": {
845
- "content": "[unused72]",
846
- "lstrip": false,
847
- "normalized": true,
848
- "rstrip": false,
849
- "single_word": false,
850
- "special": false
851
- },
852
- "50358": {
853
- "content": "[unused73]",
854
- "lstrip": false,
855
- "normalized": true,
856
- "rstrip": false,
857
- "single_word": false,
858
- "special": false
859
- },
860
- "50359": {
861
- "content": "[unused74]",
862
- "lstrip": false,
863
- "normalized": true,
864
- "rstrip": false,
865
- "single_word": false,
866
- "special": false
867
- },
868
- "50360": {
869
- "content": "[unused75]",
870
- "lstrip": false,
871
- "normalized": true,
872
- "rstrip": false,
873
- "single_word": false,
874
- "special": false
875
- },
876
- "50361": {
877
- "content": "[unused76]",
878
- "lstrip": false,
879
- "normalized": true,
880
- "rstrip": false,
881
- "single_word": false,
882
- "special": false
883
- },
884
- "50362": {
885
- "content": "[unused77]",
886
- "lstrip": false,
887
- "normalized": true,
888
- "rstrip": false,
889
- "single_word": false,
890
- "special": false
891
- },
892
- "50363": {
893
- "content": "[unused78]",
894
- "lstrip": false,
895
- "normalized": true,
896
- "rstrip": false,
897
- "single_word": false,
898
- "special": false
899
- },
900
- "50364": {
901
- "content": "[unused79]",
902
- "lstrip": false,
903
- "normalized": true,
904
- "rstrip": false,
905
- "single_word": false,
906
- "special": false
907
- },
908
- "50365": {
909
- "content": "[unused80]",
910
- "lstrip": false,
911
- "normalized": true,
912
- "rstrip": false,
913
- "single_word": false,
914
- "special": false
915
- },
916
- "50366": {
917
- "content": "[unused81]",
918
- "lstrip": false,
919
- "normalized": true,
920
- "rstrip": false,
921
- "single_word": false,
922
- "special": false
923
- },
924
- "50367": {
925
- "content": "[unused82]",
926
- "lstrip": false,
927
- "normalized": true,
928
- "rstrip": false,
929
- "single_word": false,
930
- "special": false
931
  }
932
  },
933
  "clean_up_tokenization_spaces": true,
934
  "cls_token": "[CLS]",
 
935
  "extra_special_tokens": {},
936
  "mask_token": "[MASK]",
937
- "model_input_names": [
938
- "input_ids",
939
- "attention_mask"
940
- ],
941
- "model_max_length": 1000000000000000019884624838656,
942
  "pad_token": "[PAD]",
 
 
943
  "sep_token": "[SEP]",
944
- "tokenizer_class": "PreTrainedTokenizerFast",
 
 
 
 
 
945
  "unk_token": "[UNK]"
946
  }
 
1
  {
 
2
  "added_tokens_decoder": {
3
  "0": {
4
+ "content": "[PAD]",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5
  "lstrip": false,
6
  "normalized": false,
7
  "rstrip": false,
8
  "single_word": false,
9
  "special": true
10
  },
11
+ "100": {
12
  "content": "[UNK]",
13
  "lstrip": false,
14
  "normalized": false,
 
16
  "single_word": false,
17
  "special": true
18
  },
19
+ "101": {
20
  "content": "[CLS]",
21
  "lstrip": false,
22
  "normalized": false,
 
24
  "single_word": false,
25
  "special": true
26
  },
27
+ "102": {
28
  "content": "[SEP]",
29
  "lstrip": false,
30
  "normalized": false,
 
32
  "single_word": false,
33
  "special": true
34
  },
35
+ "103": {
 
 
 
 
 
 
 
 
36
  "content": "[MASK]",
37
+ "lstrip": false,
38
  "normalized": false,
39
  "rstrip": false,
40
  "single_word": false,
41
  "special": true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
42
  }
43
  },
44
  "clean_up_tokenization_spaces": true,
45
  "cls_token": "[CLS]",
46
+ "do_lower_case": true,
47
  "extra_special_tokens": {},
48
  "mask_token": "[MASK]",
49
+ "max_length": 512,
50
+ "model_max_length": 512,
51
+ "pad_to_multiple_of": null,
 
 
52
  "pad_token": "[PAD]",
53
+ "pad_token_type_id": 0,
54
+ "padding_side": "right",
55
  "sep_token": "[SEP]",
56
+ "stride": 0,
57
+ "strip_accents": null,
58
+ "tokenize_chinese_chars": true,
59
+ "tokenizer_class": "BertTokenizer",
60
+ "truncation_side": "right",
61
+ "truncation_strategy": "longest_first",
62
  "unk_token": "[UNK]"
63
  }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff