JiyangZhang commited on
Commit
c314db4
1 Parent(s): a8fe203

Upload tokenizer

Browse files
Files changed (5) hide show
  1. added_tokens.json +26 -0
  2. merges.txt +0 -0
  3. special_tokens_map.json +753 -0
  4. tokenizer_config.json +65 -0
  5. vocab.json +0 -0
added_tokens.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<DELETE>": 32120,
3
+ "<DELETE_END>": 32121,
4
+ "<INSERT>": 32112,
5
+ "<INSERT_END>": 32115,
6
+ "<INSERT_NEW>": 32114,
7
+ "<INSERT_NEW_KEEP_AFTER>": 32119,
8
+ "<INSERT_NEW_KEEP_BEFORE>": 32117,
9
+ "<INSERT_OLD>": 32113,
10
+ "<INSERT_OLD_KEEP_AFTER>": 32118,
11
+ "<INSERT_OLD_KEEP_BEFORE>": 32116,
12
+ "<KEEP>": 32122,
13
+ "<KEEP_END>": 32123,
14
+ "<REPLACE>": 32100,
15
+ "<REPLACE_END>": 32103,
16
+ "<REPLACE_NEW>": 32102,
17
+ "<REPLACE_NEW_DELETE_KEEP_AFTER>": 32111,
18
+ "<REPLACE_NEW_DELETE_KEEP_BEFORE>": 32109,
19
+ "<REPLACE_NEW_KEEP_AFTER>": 32107,
20
+ "<REPLACE_NEW_KEEP_BEFORE>": 32105,
21
+ "<REPLACE_OLD>": 32101,
22
+ "<REPLACE_OLD_DELETE_KEEP_AFTER>": 32110,
23
+ "<REPLACE_OLD_DELETE_KEEP_BEFORE>": 32108,
24
+ "<REPLACE_OLD_KEEP_AFTER>": 32106,
25
+ "<REPLACE_OLD_KEEP_BEFORE>": 32104
26
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,753 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<extra_id_99>",
5
+ "lstrip": true,
6
+ "normalized": true,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ {
11
+ "content": "<extra_id_98>",
12
+ "lstrip": true,
13
+ "normalized": true,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ },
17
+ {
18
+ "content": "<extra_id_97>",
19
+ "lstrip": true,
20
+ "normalized": true,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ {
25
+ "content": "<extra_id_96>",
26
+ "lstrip": true,
27
+ "normalized": true,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ },
31
+ {
32
+ "content": "<extra_id_95>",
33
+ "lstrip": true,
34
+ "normalized": true,
35
+ "rstrip": false,
36
+ "single_word": false
37
+ },
38
+ {
39
+ "content": "<extra_id_94>",
40
+ "lstrip": true,
41
+ "normalized": true,
42
+ "rstrip": false,
43
+ "single_word": false
44
+ },
45
+ {
46
+ "content": "<extra_id_93>",
47
+ "lstrip": true,
48
+ "normalized": true,
49
+ "rstrip": false,
50
+ "single_word": false
51
+ },
52
+ {
53
+ "content": "<extra_id_92>",
54
+ "lstrip": true,
55
+ "normalized": true,
56
+ "rstrip": false,
57
+ "single_word": false
58
+ },
59
+ {
60
+ "content": "<extra_id_91>",
61
+ "lstrip": true,
62
+ "normalized": true,
63
+ "rstrip": false,
64
+ "single_word": false
65
+ },
66
+ {
67
+ "content": "<extra_id_90>",
68
+ "lstrip": true,
69
+ "normalized": true,
70
+ "rstrip": false,
71
+ "single_word": false
72
+ },
73
+ {
74
+ "content": "<extra_id_89>",
75
+ "lstrip": true,
76
+ "normalized": true,
77
+ "rstrip": false,
78
+ "single_word": false
79
+ },
80
+ {
81
+ "content": "<extra_id_88>",
82
+ "lstrip": true,
83
+ "normalized": true,
84
+ "rstrip": false,
85
+ "single_word": false
86
+ },
87
+ {
88
+ "content": "<extra_id_87>",
89
+ "lstrip": true,
90
+ "normalized": true,
91
+ "rstrip": false,
92
+ "single_word": false
93
+ },
94
+ {
95
+ "content": "<extra_id_86>",
96
+ "lstrip": true,
97
+ "normalized": true,
98
+ "rstrip": false,
99
+ "single_word": false
100
+ },
101
+ {
102
+ "content": "<extra_id_85>",
103
+ "lstrip": true,
104
+ "normalized": true,
105
+ "rstrip": false,
106
+ "single_word": false
107
+ },
108
+ {
109
+ "content": "<extra_id_84>",
110
+ "lstrip": true,
111
+ "normalized": true,
112
+ "rstrip": false,
113
+ "single_word": false
114
+ },
115
+ {
116
+ "content": "<extra_id_83>",
117
+ "lstrip": true,
118
+ "normalized": true,
119
+ "rstrip": false,
120
+ "single_word": false
121
+ },
122
+ {
123
+ "content": "<extra_id_82>",
124
+ "lstrip": true,
125
+ "normalized": true,
126
+ "rstrip": false,
127
+ "single_word": false
128
+ },
129
+ {
130
+ "content": "<extra_id_81>",
131
+ "lstrip": true,
132
+ "normalized": true,
133
+ "rstrip": false,
134
+ "single_word": false
135
+ },
136
+ {
137
+ "content": "<extra_id_80>",
138
+ "lstrip": true,
139
+ "normalized": true,
140
+ "rstrip": false,
141
+ "single_word": false
142
+ },
143
+ {
144
+ "content": "<extra_id_79>",
145
+ "lstrip": true,
146
+ "normalized": true,
147
+ "rstrip": false,
148
+ "single_word": false
149
+ },
150
+ {
151
+ "content": "<extra_id_78>",
152
+ "lstrip": true,
153
+ "normalized": true,
154
+ "rstrip": false,
155
+ "single_word": false
156
+ },
157
+ {
158
+ "content": "<extra_id_77>",
159
+ "lstrip": true,
160
+ "normalized": true,
161
+ "rstrip": false,
162
+ "single_word": false
163
+ },
164
+ {
165
+ "content": "<extra_id_76>",
166
+ "lstrip": true,
167
+ "normalized": true,
168
+ "rstrip": false,
169
+ "single_word": false
170
+ },
171
+ {
172
+ "content": "<extra_id_75>",
173
+ "lstrip": true,
174
+ "normalized": true,
175
+ "rstrip": false,
176
+ "single_word": false
177
+ },
178
+ {
179
+ "content": "<extra_id_74>",
180
+ "lstrip": true,
181
+ "normalized": true,
182
+ "rstrip": false,
183
+ "single_word": false
184
+ },
185
+ {
186
+ "content": "<extra_id_73>",
187
+ "lstrip": true,
188
+ "normalized": true,
189
+ "rstrip": false,
190
+ "single_word": false
191
+ },
192
+ {
193
+ "content": "<extra_id_72>",
194
+ "lstrip": true,
195
+ "normalized": true,
196
+ "rstrip": false,
197
+ "single_word": false
198
+ },
199
+ {
200
+ "content": "<extra_id_71>",
201
+ "lstrip": true,
202
+ "normalized": true,
203
+ "rstrip": false,
204
+ "single_word": false
205
+ },
206
+ {
207
+ "content": "<extra_id_70>",
208
+ "lstrip": true,
209
+ "normalized": true,
210
+ "rstrip": false,
211
+ "single_word": false
212
+ },
213
+ {
214
+ "content": "<extra_id_69>",
215
+ "lstrip": true,
216
+ "normalized": true,
217
+ "rstrip": false,
218
+ "single_word": false
219
+ },
220
+ {
221
+ "content": "<extra_id_68>",
222
+ "lstrip": true,
223
+ "normalized": true,
224
+ "rstrip": false,
225
+ "single_word": false
226
+ },
227
+ {
228
+ "content": "<extra_id_67>",
229
+ "lstrip": true,
230
+ "normalized": true,
231
+ "rstrip": false,
232
+ "single_word": false
233
+ },
234
+ {
235
+ "content": "<extra_id_66>",
236
+ "lstrip": true,
237
+ "normalized": true,
238
+ "rstrip": false,
239
+ "single_word": false
240
+ },
241
+ {
242
+ "content": "<extra_id_65>",
243
+ "lstrip": true,
244
+ "normalized": true,
245
+ "rstrip": false,
246
+ "single_word": false
247
+ },
248
+ {
249
+ "content": "<extra_id_64>",
250
+ "lstrip": true,
251
+ "normalized": true,
252
+ "rstrip": false,
253
+ "single_word": false
254
+ },
255
+ {
256
+ "content": "<extra_id_63>",
257
+ "lstrip": true,
258
+ "normalized": true,
259
+ "rstrip": false,
260
+ "single_word": false
261
+ },
262
+ {
263
+ "content": "<extra_id_62>",
264
+ "lstrip": true,
265
+ "normalized": true,
266
+ "rstrip": false,
267
+ "single_word": false
268
+ },
269
+ {
270
+ "content": "<extra_id_61>",
271
+ "lstrip": true,
272
+ "normalized": true,
273
+ "rstrip": false,
274
+ "single_word": false
275
+ },
276
+ {
277
+ "content": "<extra_id_60>",
278
+ "lstrip": true,
279
+ "normalized": true,
280
+ "rstrip": false,
281
+ "single_word": false
282
+ },
283
+ {
284
+ "content": "<extra_id_59>",
285
+ "lstrip": true,
286
+ "normalized": true,
287
+ "rstrip": false,
288
+ "single_word": false
289
+ },
290
+ {
291
+ "content": "<extra_id_58>",
292
+ "lstrip": true,
293
+ "normalized": true,
294
+ "rstrip": false,
295
+ "single_word": false
296
+ },
297
+ {
298
+ "content": "<extra_id_57>",
299
+ "lstrip": true,
300
+ "normalized": true,
301
+ "rstrip": false,
302
+ "single_word": false
303
+ },
304
+ {
305
+ "content": "<extra_id_56>",
306
+ "lstrip": true,
307
+ "normalized": true,
308
+ "rstrip": false,
309
+ "single_word": false
310
+ },
311
+ {
312
+ "content": "<extra_id_55>",
313
+ "lstrip": true,
314
+ "normalized": true,
315
+ "rstrip": false,
316
+ "single_word": false
317
+ },
318
+ {
319
+ "content": "<extra_id_54>",
320
+ "lstrip": true,
321
+ "normalized": true,
322
+ "rstrip": false,
323
+ "single_word": false
324
+ },
325
+ {
326
+ "content": "<extra_id_53>",
327
+ "lstrip": true,
328
+ "normalized": true,
329
+ "rstrip": false,
330
+ "single_word": false
331
+ },
332
+ {
333
+ "content": "<extra_id_52>",
334
+ "lstrip": true,
335
+ "normalized": true,
336
+ "rstrip": false,
337
+ "single_word": false
338
+ },
339
+ {
340
+ "content": "<extra_id_51>",
341
+ "lstrip": true,
342
+ "normalized": true,
343
+ "rstrip": false,
344
+ "single_word": false
345
+ },
346
+ {
347
+ "content": "<extra_id_50>",
348
+ "lstrip": true,
349
+ "normalized": true,
350
+ "rstrip": false,
351
+ "single_word": false
352
+ },
353
+ {
354
+ "content": "<extra_id_49>",
355
+ "lstrip": true,
356
+ "normalized": true,
357
+ "rstrip": false,
358
+ "single_word": false
359
+ },
360
+ {
361
+ "content": "<extra_id_48>",
362
+ "lstrip": true,
363
+ "normalized": true,
364
+ "rstrip": false,
365
+ "single_word": false
366
+ },
367
+ {
368
+ "content": "<extra_id_47>",
369
+ "lstrip": true,
370
+ "normalized": true,
371
+ "rstrip": false,
372
+ "single_word": false
373
+ },
374
+ {
375
+ "content": "<extra_id_46>",
376
+ "lstrip": true,
377
+ "normalized": true,
378
+ "rstrip": false,
379
+ "single_word": false
380
+ },
381
+ {
382
+ "content": "<extra_id_45>",
383
+ "lstrip": true,
384
+ "normalized": true,
385
+ "rstrip": false,
386
+ "single_word": false
387
+ },
388
+ {
389
+ "content": "<extra_id_44>",
390
+ "lstrip": true,
391
+ "normalized": true,
392
+ "rstrip": false,
393
+ "single_word": false
394
+ },
395
+ {
396
+ "content": "<extra_id_43>",
397
+ "lstrip": true,
398
+ "normalized": true,
399
+ "rstrip": false,
400
+ "single_word": false
401
+ },
402
+ {
403
+ "content": "<extra_id_42>",
404
+ "lstrip": true,
405
+ "normalized": true,
406
+ "rstrip": false,
407
+ "single_word": false
408
+ },
409
+ {
410
+ "content": "<extra_id_41>",
411
+ "lstrip": true,
412
+ "normalized": true,
413
+ "rstrip": false,
414
+ "single_word": false
415
+ },
416
+ {
417
+ "content": "<extra_id_40>",
418
+ "lstrip": true,
419
+ "normalized": true,
420
+ "rstrip": false,
421
+ "single_word": false
422
+ },
423
+ {
424
+ "content": "<extra_id_39>",
425
+ "lstrip": true,
426
+ "normalized": true,
427
+ "rstrip": false,
428
+ "single_word": false
429
+ },
430
+ {
431
+ "content": "<extra_id_38>",
432
+ "lstrip": true,
433
+ "normalized": true,
434
+ "rstrip": false,
435
+ "single_word": false
436
+ },
437
+ {
438
+ "content": "<extra_id_37>",
439
+ "lstrip": true,
440
+ "normalized": true,
441
+ "rstrip": false,
442
+ "single_word": false
443
+ },
444
+ {
445
+ "content": "<extra_id_36>",
446
+ "lstrip": true,
447
+ "normalized": true,
448
+ "rstrip": false,
449
+ "single_word": false
450
+ },
451
+ {
452
+ "content": "<extra_id_35>",
453
+ "lstrip": true,
454
+ "normalized": true,
455
+ "rstrip": false,
456
+ "single_word": false
457
+ },
458
+ {
459
+ "content": "<extra_id_34>",
460
+ "lstrip": true,
461
+ "normalized": true,
462
+ "rstrip": false,
463
+ "single_word": false
464
+ },
465
+ {
466
+ "content": "<extra_id_33>",
467
+ "lstrip": true,
468
+ "normalized": true,
469
+ "rstrip": false,
470
+ "single_word": false
471
+ },
472
+ {
473
+ "content": "<extra_id_32>",
474
+ "lstrip": true,
475
+ "normalized": true,
476
+ "rstrip": false,
477
+ "single_word": false
478
+ },
479
+ {
480
+ "content": "<extra_id_31>",
481
+ "lstrip": true,
482
+ "normalized": true,
483
+ "rstrip": false,
484
+ "single_word": false
485
+ },
486
+ {
487
+ "content": "<extra_id_30>",
488
+ "lstrip": true,
489
+ "normalized": true,
490
+ "rstrip": false,
491
+ "single_word": false
492
+ },
493
+ {
494
+ "content": "<extra_id_29>",
495
+ "lstrip": true,
496
+ "normalized": true,
497
+ "rstrip": false,
498
+ "single_word": false
499
+ },
500
+ {
501
+ "content": "<extra_id_28>",
502
+ "lstrip": true,
503
+ "normalized": true,
504
+ "rstrip": false,
505
+ "single_word": false
506
+ },
507
+ {
508
+ "content": "<extra_id_27>",
509
+ "lstrip": true,
510
+ "normalized": true,
511
+ "rstrip": false,
512
+ "single_word": false
513
+ },
514
+ {
515
+ "content": "<extra_id_26>",
516
+ "lstrip": true,
517
+ "normalized": true,
518
+ "rstrip": false,
519
+ "single_word": false
520
+ },
521
+ {
522
+ "content": "<extra_id_25>",
523
+ "lstrip": true,
524
+ "normalized": true,
525
+ "rstrip": false,
526
+ "single_word": false
527
+ },
528
+ {
529
+ "content": "<extra_id_24>",
530
+ "lstrip": true,
531
+ "normalized": true,
532
+ "rstrip": false,
533
+ "single_word": false
534
+ },
535
+ {
536
+ "content": "<extra_id_23>",
537
+ "lstrip": true,
538
+ "normalized": true,
539
+ "rstrip": false,
540
+ "single_word": false
541
+ },
542
+ {
543
+ "content": "<extra_id_22>",
544
+ "lstrip": true,
545
+ "normalized": true,
546
+ "rstrip": false,
547
+ "single_word": false
548
+ },
549
+ {
550
+ "content": "<extra_id_21>",
551
+ "lstrip": true,
552
+ "normalized": true,
553
+ "rstrip": false,
554
+ "single_word": false
555
+ },
556
+ {
557
+ "content": "<extra_id_20>",
558
+ "lstrip": true,
559
+ "normalized": true,
560
+ "rstrip": false,
561
+ "single_word": false
562
+ },
563
+ {
564
+ "content": "<extra_id_19>",
565
+ "lstrip": true,
566
+ "normalized": true,
567
+ "rstrip": false,
568
+ "single_word": false
569
+ },
570
+ {
571
+ "content": "<extra_id_18>",
572
+ "lstrip": true,
573
+ "normalized": true,
574
+ "rstrip": false,
575
+ "single_word": false
576
+ },
577
+ {
578
+ "content": "<extra_id_17>",
579
+ "lstrip": true,
580
+ "normalized": true,
581
+ "rstrip": false,
582
+ "single_word": false
583
+ },
584
+ {
585
+ "content": "<extra_id_16>",
586
+ "lstrip": true,
587
+ "normalized": true,
588
+ "rstrip": false,
589
+ "single_word": false
590
+ },
591
+ {
592
+ "content": "<extra_id_15>",
593
+ "lstrip": true,
594
+ "normalized": true,
595
+ "rstrip": false,
596
+ "single_word": false
597
+ },
598
+ {
599
+ "content": "<extra_id_14>",
600
+ "lstrip": true,
601
+ "normalized": true,
602
+ "rstrip": false,
603
+ "single_word": false
604
+ },
605
+ {
606
+ "content": "<extra_id_13>",
607
+ "lstrip": true,
608
+ "normalized": true,
609
+ "rstrip": false,
610
+ "single_word": false
611
+ },
612
+ {
613
+ "content": "<extra_id_12>",
614
+ "lstrip": true,
615
+ "normalized": true,
616
+ "rstrip": false,
617
+ "single_word": false
618
+ },
619
+ {
620
+ "content": "<extra_id_11>",
621
+ "lstrip": true,
622
+ "normalized": true,
623
+ "rstrip": false,
624
+ "single_word": false
625
+ },
626
+ {
627
+ "content": "<extra_id_10>",
628
+ "lstrip": true,
629
+ "normalized": true,
630
+ "rstrip": false,
631
+ "single_word": false
632
+ },
633
+ {
634
+ "content": "<extra_id_9>",
635
+ "lstrip": true,
636
+ "normalized": true,
637
+ "rstrip": false,
638
+ "single_word": false
639
+ },
640
+ {
641
+ "content": "<extra_id_8>",
642
+ "lstrip": true,
643
+ "normalized": true,
644
+ "rstrip": false,
645
+ "single_word": false
646
+ },
647
+ {
648
+ "content": "<extra_id_7>",
649
+ "lstrip": true,
650
+ "normalized": true,
651
+ "rstrip": false,
652
+ "single_word": false
653
+ },
654
+ {
655
+ "content": "<extra_id_6>",
656
+ "lstrip": true,
657
+ "normalized": true,
658
+ "rstrip": false,
659
+ "single_word": false
660
+ },
661
+ {
662
+ "content": "<extra_id_5>",
663
+ "lstrip": true,
664
+ "normalized": true,
665
+ "rstrip": false,
666
+ "single_word": false
667
+ },
668
+ {
669
+ "content": "<extra_id_4>",
670
+ "lstrip": true,
671
+ "normalized": true,
672
+ "rstrip": false,
673
+ "single_word": false
674
+ },
675
+ {
676
+ "content": "<extra_id_3>",
677
+ "lstrip": true,
678
+ "normalized": true,
679
+ "rstrip": false,
680
+ "single_word": false
681
+ },
682
+ {
683
+ "content": "<extra_id_2>",
684
+ "lstrip": true,
685
+ "normalized": true,
686
+ "rstrip": false,
687
+ "single_word": false
688
+ },
689
+ {
690
+ "content": "<extra_id_1>",
691
+ "lstrip": true,
692
+ "normalized": true,
693
+ "rstrip": false,
694
+ "single_word": false
695
+ },
696
+ {
697
+ "content": "<extra_id_0>",
698
+ "lstrip": true,
699
+ "normalized": true,
700
+ "rstrip": false,
701
+ "single_word": false
702
+ }
703
+ ],
704
+ "bos_token": {
705
+ "content": "<s>",
706
+ "lstrip": false,
707
+ "normalized": true,
708
+ "rstrip": false,
709
+ "single_word": false
710
+ },
711
+ "cls_token": {
712
+ "content": "<s>",
713
+ "lstrip": false,
714
+ "normalized": true,
715
+ "rstrip": false,
716
+ "single_word": false
717
+ },
718
+ "eos_token": {
719
+ "content": "</s>",
720
+ "lstrip": false,
721
+ "normalized": true,
722
+ "rstrip": false,
723
+ "single_word": false
724
+ },
725
+ "mask_token": {
726
+ "content": "<mask>",
727
+ "lstrip": true,
728
+ "normalized": true,
729
+ "rstrip": false,
730
+ "single_word": false
731
+ },
732
+ "pad_token": {
733
+ "content": "<pad>",
734
+ "lstrip": false,
735
+ "normalized": true,
736
+ "rstrip": false,
737
+ "single_word": false
738
+ },
739
+ "sep_token": {
740
+ "content": "</s>",
741
+ "lstrip": false,
742
+ "normalized": true,
743
+ "rstrip": false,
744
+ "single_word": false
745
+ },
746
+ "unk_token": {
747
+ "content": "<unk>",
748
+ "lstrip": false,
749
+ "normalized": true,
750
+ "rstrip": false,
751
+ "single_word": false
752
+ }
753
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": {
4
+ "__type": "AddedToken",
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false
10
+ },
11
+ "cls_token": {
12
+ "__type": "AddedToken",
13
+ "content": "<s>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false
18
+ },
19
+ "eos_token": {
20
+ "__type": "AddedToken",
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false
26
+ },
27
+ "errors": "replace",
28
+ "mask_token": {
29
+ "__type": "AddedToken",
30
+ "content": "<mask>",
31
+ "lstrip": true,
32
+ "normalized": true,
33
+ "rstrip": false,
34
+ "single_word": false
35
+ },
36
+ "model_max_length": 512,
37
+ "name_or_path": "../models/codeT5Tokenizer",
38
+ "pad_token": {
39
+ "__type": "AddedToken",
40
+ "content": "<pad>",
41
+ "lstrip": false,
42
+ "normalized": true,
43
+ "rstrip": false,
44
+ "single_word": false
45
+ },
46
+ "sep_token": {
47
+ "__type": "AddedToken",
48
+ "content": "</s>",
49
+ "lstrip": false,
50
+ "normalized": true,
51
+ "rstrip": false,
52
+ "single_word": false
53
+ },
54
+ "special_tokens_map_file": "/work2/06922/jiyang/maverick2/.cache/5941df5e4315c5ab63b7b2ac791fb0bf0f209744a055c06b43b5274849137cdd.b9905d0575bde443a20834122b6e2d48e853b2e36444ce98ddeb43c38097eb3f",
55
+ "tokenizer_class": "RobertaTokenizer",
56
+ "tokenizer_file": null,
57
+ "unk_token": {
58
+ "__type": "AddedToken",
59
+ "content": "<unk>",
60
+ "lstrip": false,
61
+ "normalized": true,
62
+ "rstrip": false,
63
+ "single_word": false
64
+ }
65
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff