tistak commited on
Commit
0cd2bcb
1 Parent(s): 303d26c

Upload tokenizer

Browse files
Files changed (6) hide show
  1. added_tokens.json +3 -0
  2. merges.txt +0 -0
  3. special_tokens_map.json +50 -1
  4. tokenizer.json +0 -0
  5. tokenizer_config.json +111 -1853
  6. vocab.json +0 -0
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<|end_of_text|>": 100289
3
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json CHANGED
@@ -1,16 +1,65 @@
1
  {
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2
  "bos_token": {
3
- "content": "<|begin_of_text|>",
4
  "lstrip": false,
5
  "normalized": false,
6
  "rstrip": false,
7
  "single_word": false
8
  },
9
  "eos_token": {
 
 
 
 
 
 
 
10
  "content": "<|end_of_text|>",
11
  "lstrip": false,
12
  "normalized": false,
13
  "rstrip": false,
14
  "single_word": false
 
 
 
 
 
 
 
15
  }
16
  }
 
1
  {
2
+ "additional_special_tokens": [
3
+ "<|reg_extra|>",
4
+ "<|endoftext|>",
5
+ "<|fim_prefix|>",
6
+ "<|fim_middle|>",
7
+ "<|fim_suffix|>",
8
+ "<|fim_pad|>",
9
+ "<gh_stars>",
10
+ "<filename>",
11
+ "<issue_start>",
12
+ "<issue_comment>",
13
+ "<issue_closed>",
14
+ "<jupyter_start>",
15
+ "<jupyter_text>",
16
+ "<jupyter_code>",
17
+ "<jupyter_output>",
18
+ "<empty_output>",
19
+ "<commit_before>",
20
+ "<commit_msg>",
21
+ "<commit_after>",
22
+ "<reponame>",
23
+ "<|endofprompt|>",
24
+ "<|im_start|>",
25
+ "<|im_end|>",
26
+ "<|pause|>",
27
+ "<|reg0|>",
28
+ "<|reg1|>",
29
+ "<|reg2|>",
30
+ "<|reg3|>",
31
+ "<|reg4|>",
32
+ "<|reg5|>",
33
+ "<|reg6|>",
34
+ "<|reg7|>",
35
+ "<|extra0|>"
36
+ ],
37
  "bos_token": {
38
+ "content": "<|endoftext|>",
39
  "lstrip": false,
40
  "normalized": false,
41
  "rstrip": false,
42
  "single_word": false
43
  },
44
  "eos_token": {
45
+ "content": "<|endoftext|>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ },
51
+ "pad_token": {
52
  "content": "<|end_of_text|>",
53
  "lstrip": false,
54
  "normalized": false,
55
  "rstrip": false,
56
  "single_word": false
57
+ },
58
+ "unk_token": {
59
+ "content": "<|endoftext|>",
60
+ "lstrip": false,
61
+ "normalized": false,
62
+ "rstrip": false,
63
+ "single_word": false
64
  }
65
  }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,2047 +1,272 @@
1
  {
 
2
  "added_tokens_decoder": {
3
- "128000": {
4
- "content": "<|begin_of_text|>",
5
  "lstrip": false,
6
  "normalized": false,
7
  "rstrip": false,
8
  "single_word": false,
9
  "special": true
10
  },
11
- "128001": {
12
- "content": "<|end_of_text|>",
13
- "lstrip": false,
14
- "normalized": false,
15
- "rstrip": false,
16
- "single_word": false,
17
- "special": true
18
- },
19
- "128002": {
20
- "content": "<|reserved_special_token_0|>",
21
- "lstrip": false,
22
- "normalized": false,
23
- "rstrip": false,
24
- "single_word": false,
25
- "special": true
26
- },
27
- "128003": {
28
- "content": "<|reserved_special_token_1|>",
29
- "lstrip": false,
30
- "normalized": false,
31
- "rstrip": false,
32
- "single_word": false,
33
- "special": true
34
- },
35
- "128004": {
36
- "content": "<|reserved_special_token_2|>",
37
- "lstrip": false,
38
- "normalized": false,
39
- "rstrip": false,
40
- "single_word": false,
41
- "special": true
42
- },
43
- "128005": {
44
- "content": "<|reserved_special_token_3|>",
45
- "lstrip": false,
46
- "normalized": false,
47
- "rstrip": false,
48
- "single_word": false,
49
- "special": true
50
- },
51
- "128006": {
52
- "content": "<|start_header_id|>",
53
- "lstrip": false,
54
- "normalized": false,
55
- "rstrip": false,
56
- "single_word": false,
57
- "special": true
58
- },
59
- "128007": {
60
- "content": "<|end_header_id|>",
61
- "lstrip": false,
62
- "normalized": false,
63
- "rstrip": false,
64
- "single_word": false,
65
- "special": true
66
- },
67
- "128008": {
68
- "content": "<|reserved_special_token_4|>",
69
- "lstrip": false,
70
- "normalized": false,
71
- "rstrip": false,
72
- "single_word": false,
73
- "special": true
74
- },
75
- "128009": {
76
- "content": "<|eot_id|>",
77
- "lstrip": false,
78
- "normalized": false,
79
- "rstrip": false,
80
- "single_word": false,
81
- "special": true
82
- },
83
- "128010": {
84
- "content": "<|reserved_special_token_5|>",
85
- "lstrip": false,
86
- "normalized": false,
87
- "rstrip": false,
88
- "single_word": false,
89
- "special": true
90
- },
91
- "128011": {
92
- "content": "<|reserved_special_token_6|>",
93
- "lstrip": false,
94
- "normalized": false,
95
- "rstrip": false,
96
- "single_word": false,
97
- "special": true
98
- },
99
- "128012": {
100
- "content": "<|reserved_special_token_7|>",
101
- "lstrip": false,
102
- "normalized": false,
103
- "rstrip": false,
104
- "single_word": false,
105
- "special": true
106
- },
107
- "128013": {
108
- "content": "<|reserved_special_token_8|>",
109
- "lstrip": false,
110
- "normalized": false,
111
- "rstrip": false,
112
- "single_word": false,
113
- "special": true
114
- },
115
- "128014": {
116
- "content": "<|reserved_special_token_9|>",
117
- "lstrip": false,
118
- "normalized": false,
119
- "rstrip": false,
120
- "single_word": false,
121
- "special": true
122
- },
123
- "128015": {
124
- "content": "<|reserved_special_token_10|>",
125
- "lstrip": false,
126
- "normalized": false,
127
- "rstrip": false,
128
- "single_word": false,
129
- "special": true
130
- },
131
- "128016": {
132
- "content": "<|reserved_special_token_11|>",
133
- "lstrip": false,
134
- "normalized": false,
135
- "rstrip": false,
136
- "single_word": false,
137
- "special": true
138
- },
139
- "128017": {
140
- "content": "<|reserved_special_token_12|>",
141
- "lstrip": false,
142
- "normalized": false,
143
- "rstrip": false,
144
- "single_word": false,
145
- "special": true
146
- },
147
- "128018": {
148
- "content": "<|reserved_special_token_13|>",
149
- "lstrip": false,
150
- "normalized": false,
151
- "rstrip": false,
152
- "single_word": false,
153
- "special": true
154
- },
155
- "128019": {
156
- "content": "<|reserved_special_token_14|>",
157
- "lstrip": false,
158
- "normalized": false,
159
- "rstrip": false,
160
- "single_word": false,
161
- "special": true
162
- },
163
- "128020": {
164
- "content": "<|reserved_special_token_15|>",
165
- "lstrip": false,
166
- "normalized": false,
167
- "rstrip": false,
168
- "single_word": false,
169
- "special": true
170
- },
171
- "128021": {
172
- "content": "<|reserved_special_token_16|>",
173
- "lstrip": false,
174
- "normalized": false,
175
- "rstrip": false,
176
- "single_word": false,
177
- "special": true
178
- },
179
- "128022": {
180
- "content": "<|reserved_special_token_17|>",
181
- "lstrip": false,
182
- "normalized": false,
183
- "rstrip": false,
184
- "single_word": false,
185
- "special": true
186
- },
187
- "128023": {
188
- "content": "<|reserved_special_token_18|>",
189
- "lstrip": false,
190
- "normalized": false,
191
- "rstrip": false,
192
- "single_word": false,
193
- "special": true
194
- },
195
- "128024": {
196
- "content": "<|reserved_special_token_19|>",
197
- "lstrip": false,
198
- "normalized": false,
199
- "rstrip": false,
200
- "single_word": false,
201
- "special": true
202
- },
203
- "128025": {
204
- "content": "<|reserved_special_token_20|>",
205
- "lstrip": false,
206
- "normalized": false,
207
- "rstrip": false,
208
- "single_word": false,
209
- "special": true
210
- },
211
- "128026": {
212
- "content": "<|reserved_special_token_21|>",
213
- "lstrip": false,
214
- "normalized": false,
215
- "rstrip": false,
216
- "single_word": false,
217
- "special": true
218
- },
219
- "128027": {
220
- "content": "<|reserved_special_token_22|>",
221
- "lstrip": false,
222
- "normalized": false,
223
- "rstrip": false,
224
- "single_word": false,
225
- "special": true
226
- },
227
- "128028": {
228
- "content": "<|reserved_special_token_23|>",
229
- "lstrip": false,
230
- "normalized": false,
231
- "rstrip": false,
232
- "single_word": false,
233
- "special": true
234
- },
235
- "128029": {
236
- "content": "<|reserved_special_token_24|>",
237
- "lstrip": false,
238
- "normalized": false,
239
- "rstrip": false,
240
- "single_word": false,
241
- "special": true
242
- },
243
- "128030": {
244
- "content": "<|reserved_special_token_25|>",
245
- "lstrip": false,
246
- "normalized": false,
247
- "rstrip": false,
248
- "single_word": false,
249
- "special": true
250
- },
251
- "128031": {
252
- "content": "<|reserved_special_token_26|>",
253
- "lstrip": false,
254
- "normalized": false,
255
- "rstrip": false,
256
- "single_word": false,
257
- "special": true
258
- },
259
- "128032": {
260
- "content": "<|reserved_special_token_27|>",
261
- "lstrip": false,
262
- "normalized": false,
263
- "rstrip": false,
264
- "single_word": false,
265
- "special": true
266
- },
267
- "128033": {
268
- "content": "<|reserved_special_token_28|>",
269
- "lstrip": false,
270
- "normalized": false,
271
- "rstrip": false,
272
- "single_word": false,
273
- "special": true
274
- },
275
- "128034": {
276
- "content": "<|reserved_special_token_29|>",
277
- "lstrip": false,
278
- "normalized": false,
279
- "rstrip": false,
280
- "single_word": false,
281
- "special": true
282
- },
283
- "128035": {
284
- "content": "<|reserved_special_token_30|>",
285
- "lstrip": false,
286
- "normalized": false,
287
- "rstrip": false,
288
- "single_word": false,
289
- "special": true
290
- },
291
- "128036": {
292
- "content": "<|reserved_special_token_31|>",
293
- "lstrip": false,
294
- "normalized": false,
295
- "rstrip": false,
296
- "single_word": false,
297
- "special": true
298
- },
299
- "128037": {
300
- "content": "<|reserved_special_token_32|>",
301
- "lstrip": false,
302
- "normalized": false,
303
- "rstrip": false,
304
- "single_word": false,
305
- "special": true
306
- },
307
- "128038": {
308
- "content": "<|reserved_special_token_33|>",
309
- "lstrip": false,
310
- "normalized": false,
311
- "rstrip": false,
312
- "single_word": false,
313
- "special": true
314
- },
315
- "128039": {
316
- "content": "<|reserved_special_token_34|>",
317
- "lstrip": false,
318
- "normalized": false,
319
- "rstrip": false,
320
- "single_word": false,
321
- "special": true
322
- },
323
- "128040": {
324
- "content": "<|reserved_special_token_35|>",
325
- "lstrip": false,
326
- "normalized": false,
327
- "rstrip": false,
328
- "single_word": false,
329
- "special": true
330
- },
331
- "128041": {
332
- "content": "<|reserved_special_token_36|>",
333
- "lstrip": false,
334
- "normalized": false,
335
- "rstrip": false,
336
- "single_word": false,
337
- "special": true
338
- },
339
- "128042": {
340
- "content": "<|reserved_special_token_37|>",
341
- "lstrip": false,
342
- "normalized": false,
343
- "rstrip": false,
344
- "single_word": false,
345
- "special": true
346
- },
347
- "128043": {
348
- "content": "<|reserved_special_token_38|>",
349
- "lstrip": false,
350
- "normalized": false,
351
- "rstrip": false,
352
- "single_word": false,
353
- "special": true
354
- },
355
- "128044": {
356
- "content": "<|reserved_special_token_39|>",
357
- "lstrip": false,
358
- "normalized": false,
359
- "rstrip": false,
360
- "single_word": false,
361
- "special": true
362
- },
363
- "128045": {
364
- "content": "<|reserved_special_token_40|>",
365
- "lstrip": false,
366
- "normalized": false,
367
- "rstrip": false,
368
- "single_word": false,
369
- "special": true
370
- },
371
- "128046": {
372
- "content": "<|reserved_special_token_41|>",
373
- "lstrip": false,
374
- "normalized": false,
375
- "rstrip": false,
376
- "single_word": false,
377
- "special": true
378
- },
379
- "128047": {
380
- "content": "<|reserved_special_token_42|>",
381
- "lstrip": false,
382
- "normalized": false,
383
- "rstrip": false,
384
- "single_word": false,
385
- "special": true
386
- },
387
- "128048": {
388
- "content": "<|reserved_special_token_43|>",
389
- "lstrip": false,
390
- "normalized": false,
391
- "rstrip": false,
392
- "single_word": false,
393
- "special": true
394
- },
395
- "128049": {
396
- "content": "<|reserved_special_token_44|>",
397
- "lstrip": false,
398
- "normalized": false,
399
- "rstrip": false,
400
- "single_word": false,
401
- "special": true
402
- },
403
- "128050": {
404
- "content": "<|reserved_special_token_45|>",
405
- "lstrip": false,
406
- "normalized": false,
407
- "rstrip": false,
408
- "single_word": false,
409
- "special": true
410
- },
411
- "128051": {
412
- "content": "<|reserved_special_token_46|>",
413
- "lstrip": false,
414
- "normalized": false,
415
- "rstrip": false,
416
- "single_word": false,
417
- "special": true
418
- },
419
- "128052": {
420
- "content": "<|reserved_special_token_47|>",
421
- "lstrip": false,
422
- "normalized": false,
423
- "rstrip": false,
424
- "single_word": false,
425
- "special": true
426
- },
427
- "128053": {
428
- "content": "<|reserved_special_token_48|>",
429
- "lstrip": false,
430
- "normalized": false,
431
- "rstrip": false,
432
- "single_word": false,
433
- "special": true
434
- },
435
- "128054": {
436
- "content": "<|reserved_special_token_49|>",
437
- "lstrip": false,
438
- "normalized": false,
439
- "rstrip": false,
440
- "single_word": false,
441
- "special": true
442
- },
443
- "128055": {
444
- "content": "<|reserved_special_token_50|>",
445
- "lstrip": false,
446
- "normalized": false,
447
- "rstrip": false,
448
- "single_word": false,
449
- "special": true
450
- },
451
- "128056": {
452
- "content": "<|reserved_special_token_51|>",
453
- "lstrip": false,
454
- "normalized": false,
455
- "rstrip": false,
456
- "single_word": false,
457
- "special": true
458
- },
459
- "128057": {
460
- "content": "<|reserved_special_token_52|>",
461
- "lstrip": false,
462
- "normalized": false,
463
- "rstrip": false,
464
- "single_word": false,
465
- "special": true
466
- },
467
- "128058": {
468
- "content": "<|reserved_special_token_53|>",
469
- "lstrip": false,
470
- "normalized": false,
471
- "rstrip": false,
472
- "single_word": false,
473
- "special": true
474
- },
475
- "128059": {
476
- "content": "<|reserved_special_token_54|>",
477
- "lstrip": false,
478
- "normalized": false,
479
- "rstrip": false,
480
- "single_word": false,
481
- "special": true
482
- },
483
- "128060": {
484
- "content": "<|reserved_special_token_55|>",
485
- "lstrip": false,
486
- "normalized": false,
487
- "rstrip": false,
488
- "single_word": false,
489
- "special": true
490
- },
491
- "128061": {
492
- "content": "<|reserved_special_token_56|>",
493
- "lstrip": false,
494
- "normalized": false,
495
- "rstrip": false,
496
- "single_word": false,
497
- "special": true
498
- },
499
- "128062": {
500
- "content": "<|reserved_special_token_57|>",
501
- "lstrip": false,
502
- "normalized": false,
503
- "rstrip": false,
504
- "single_word": false,
505
- "special": true
506
- },
507
- "128063": {
508
- "content": "<|reserved_special_token_58|>",
509
- "lstrip": false,
510
- "normalized": false,
511
- "rstrip": false,
512
- "single_word": false,
513
- "special": true
514
- },
515
- "128064": {
516
- "content": "<|reserved_special_token_59|>",
517
- "lstrip": false,
518
- "normalized": false,
519
- "rstrip": false,
520
- "single_word": false,
521
- "special": true
522
- },
523
- "128065": {
524
- "content": "<|reserved_special_token_60|>",
525
- "lstrip": false,
526
- "normalized": false,
527
- "rstrip": false,
528
- "single_word": false,
529
- "special": true
530
- },
531
- "128066": {
532
- "content": "<|reserved_special_token_61|>",
533
- "lstrip": false,
534
- "normalized": false,
535
- "rstrip": false,
536
- "single_word": false,
537
- "special": true
538
- },
539
- "128067": {
540
- "content": "<|reserved_special_token_62|>",
541
- "lstrip": false,
542
- "normalized": false,
543
- "rstrip": false,
544
- "single_word": false,
545
- "special": true
546
- },
547
- "128068": {
548
- "content": "<|reserved_special_token_63|>",
549
- "lstrip": false,
550
- "normalized": false,
551
- "rstrip": false,
552
- "single_word": false,
553
- "special": true
554
- },
555
- "128069": {
556
- "content": "<|reserved_special_token_64|>",
557
- "lstrip": false,
558
- "normalized": false,
559
- "rstrip": false,
560
- "single_word": false,
561
- "special": true
562
- },
563
- "128070": {
564
- "content": "<|reserved_special_token_65|>",
565
- "lstrip": false,
566
- "normalized": false,
567
- "rstrip": false,
568
- "single_word": false,
569
- "special": true
570
- },
571
- "128071": {
572
- "content": "<|reserved_special_token_66|>",
573
- "lstrip": false,
574
- "normalized": false,
575
- "rstrip": false,
576
- "single_word": false,
577
- "special": true
578
- },
579
- "128072": {
580
- "content": "<|reserved_special_token_67|>",
581
- "lstrip": false,
582
- "normalized": false,
583
- "rstrip": false,
584
- "single_word": false,
585
- "special": true
586
- },
587
- "128073": {
588
- "content": "<|reserved_special_token_68|>",
589
- "lstrip": false,
590
- "normalized": false,
591
- "rstrip": false,
592
- "single_word": false,
593
- "special": true
594
- },
595
- "128074": {
596
- "content": "<|reserved_special_token_69|>",
597
- "lstrip": false,
598
- "normalized": false,
599
- "rstrip": false,
600
- "single_word": false,
601
- "special": true
602
- },
603
- "128075": {
604
- "content": "<|reserved_special_token_70|>",
605
- "lstrip": false,
606
- "normalized": false,
607
- "rstrip": false,
608
- "single_word": false,
609
- "special": true
610
- },
611
- "128076": {
612
- "content": "<|reserved_special_token_71|>",
613
- "lstrip": false,
614
- "normalized": false,
615
- "rstrip": false,
616
- "single_word": false,
617
- "special": true
618
- },
619
- "128077": {
620
- "content": "<|reserved_special_token_72|>",
621
- "lstrip": false,
622
- "normalized": false,
623
- "rstrip": false,
624
- "single_word": false,
625
- "special": true
626
- },
627
- "128078": {
628
- "content": "<|reserved_special_token_73|>",
629
- "lstrip": false,
630
- "normalized": false,
631
- "rstrip": false,
632
- "single_word": false,
633
- "special": true
634
- },
635
- "128079": {
636
- "content": "<|reserved_special_token_74|>",
637
- "lstrip": false,
638
- "normalized": false,
639
- "rstrip": false,
640
- "single_word": false,
641
- "special": true
642
- },
643
- "128080": {
644
- "content": "<|reserved_special_token_75|>",
645
- "lstrip": false,
646
- "normalized": false,
647
- "rstrip": false,
648
- "single_word": false,
649
- "special": true
650
- },
651
- "128081": {
652
- "content": "<|reserved_special_token_76|>",
653
- "lstrip": false,
654
- "normalized": false,
655
- "rstrip": false,
656
- "single_word": false,
657
- "special": true
658
- },
659
- "128082": {
660
- "content": "<|reserved_special_token_77|>",
661
- "lstrip": false,
662
- "normalized": false,
663
- "rstrip": false,
664
- "single_word": false,
665
- "special": true
666
- },
667
- "128083": {
668
- "content": "<|reserved_special_token_78|>",
669
- "lstrip": false,
670
- "normalized": false,
671
- "rstrip": false,
672
- "single_word": false,
673
- "special": true
674
- },
675
- "128084": {
676
- "content": "<|reserved_special_token_79|>",
677
- "lstrip": false,
678
- "normalized": false,
679
- "rstrip": false,
680
- "single_word": false,
681
- "special": true
682
- },
683
- "128085": {
684
- "content": "<|reserved_special_token_80|>",
685
- "lstrip": false,
686
- "normalized": false,
687
- "rstrip": false,
688
- "single_word": false,
689
- "special": true
690
- },
691
- "128086": {
692
- "content": "<|reserved_special_token_81|>",
693
- "lstrip": false,
694
- "normalized": false,
695
- "rstrip": false,
696
- "single_word": false,
697
- "special": true
698
- },
699
- "128087": {
700
- "content": "<|reserved_special_token_82|>",
701
- "lstrip": false,
702
- "normalized": false,
703
- "rstrip": false,
704
- "single_word": false,
705
- "special": true
706
- },
707
- "128088": {
708
- "content": "<|reserved_special_token_83|>",
709
- "lstrip": false,
710
- "normalized": false,
711
- "rstrip": false,
712
- "single_word": false,
713
- "special": true
714
- },
715
- "128089": {
716
- "content": "<|reserved_special_token_84|>",
717
- "lstrip": false,
718
- "normalized": false,
719
- "rstrip": false,
720
- "single_word": false,
721
- "special": true
722
- },
723
- "128090": {
724
- "content": "<|reserved_special_token_85|>",
725
- "lstrip": false,
726
- "normalized": false,
727
- "rstrip": false,
728
- "single_word": false,
729
- "special": true
730
- },
731
- "128091": {
732
- "content": "<|reserved_special_token_86|>",
733
- "lstrip": false,
734
- "normalized": false,
735
- "rstrip": false,
736
- "single_word": false,
737
- "special": true
738
- },
739
- "128092": {
740
- "content": "<|reserved_special_token_87|>",
741
- "lstrip": false,
742
- "normalized": false,
743
- "rstrip": false,
744
- "single_word": false,
745
- "special": true
746
- },
747
- "128093": {
748
- "content": "<|reserved_special_token_88|>",
749
- "lstrip": false,
750
- "normalized": false,
751
- "rstrip": false,
752
- "single_word": false,
753
- "special": true
754
- },
755
- "128094": {
756
- "content": "<|reserved_special_token_89|>",
757
- "lstrip": false,
758
- "normalized": false,
759
- "rstrip": false,
760
- "single_word": false,
761
- "special": true
762
- },
763
- "128095": {
764
- "content": "<|reserved_special_token_90|>",
765
- "lstrip": false,
766
- "normalized": false,
767
- "rstrip": false,
768
- "single_word": false,
769
- "special": true
770
- },
771
- "128096": {
772
- "content": "<|reserved_special_token_91|>",
773
- "lstrip": false,
774
- "normalized": false,
775
- "rstrip": false,
776
- "single_word": false,
777
- "special": true
778
- },
779
- "128097": {
780
- "content": "<|reserved_special_token_92|>",
781
- "lstrip": false,
782
- "normalized": false,
783
- "rstrip": false,
784
- "single_word": false,
785
- "special": true
786
- },
787
- "128098": {
788
- "content": "<|reserved_special_token_93|>",
789
- "lstrip": false,
790
- "normalized": false,
791
- "rstrip": false,
792
- "single_word": false,
793
- "special": true
794
- },
795
- "128099": {
796
- "content": "<|reserved_special_token_94|>",
797
- "lstrip": false,
798
- "normalized": false,
799
- "rstrip": false,
800
- "single_word": false,
801
- "special": true
802
- },
803
- "128100": {
804
- "content": "<|reserved_special_token_95|>",
805
- "lstrip": false,
806
- "normalized": false,
807
- "rstrip": false,
808
- "single_word": false,
809
- "special": true
810
- },
811
- "128101": {
812
- "content": "<|reserved_special_token_96|>",
813
- "lstrip": false,
814
- "normalized": false,
815
- "rstrip": false,
816
- "single_word": false,
817
- "special": true
818
- },
819
- "128102": {
820
- "content": "<|reserved_special_token_97|>",
821
- "lstrip": false,
822
- "normalized": false,
823
- "rstrip": false,
824
- "single_word": false,
825
- "special": true
826
- },
827
- "128103": {
828
- "content": "<|reserved_special_token_98|>",
829
- "lstrip": false,
830
- "normalized": false,
831
- "rstrip": false,
832
- "single_word": false,
833
- "special": true
834
- },
835
- "128104": {
836
- "content": "<|reserved_special_token_99|>",
837
- "lstrip": false,
838
- "normalized": false,
839
- "rstrip": false,
840
- "single_word": false,
841
- "special": true
842
- },
843
- "128105": {
844
- "content": "<|reserved_special_token_100|>",
845
- "lstrip": false,
846
- "normalized": false,
847
- "rstrip": false,
848
- "single_word": false,
849
- "special": true
850
- },
851
- "128106": {
852
- "content": "<|reserved_special_token_101|>",
853
- "lstrip": false,
854
- "normalized": false,
855
- "rstrip": false,
856
- "single_word": false,
857
- "special": true
858
- },
859
- "128107": {
860
- "content": "<|reserved_special_token_102|>",
861
- "lstrip": false,
862
- "normalized": false,
863
- "rstrip": false,
864
- "single_word": false,
865
- "special": true
866
- },
867
- "128108": {
868
- "content": "<|reserved_special_token_103|>",
869
- "lstrip": false,
870
- "normalized": false,
871
- "rstrip": false,
872
- "single_word": false,
873
- "special": true
874
- },
875
- "128109": {
876
- "content": "<|reserved_special_token_104|>",
877
- "lstrip": false,
878
- "normalized": false,
879
- "rstrip": false,
880
- "single_word": false,
881
- "special": true
882
- },
883
- "128110": {
884
- "content": "<|reserved_special_token_105|>",
885
- "lstrip": false,
886
- "normalized": false,
887
- "rstrip": false,
888
- "single_word": false,
889
- "special": true
890
- },
891
- "128111": {
892
- "content": "<|reserved_special_token_106|>",
893
- "lstrip": false,
894
- "normalized": false,
895
- "rstrip": false,
896
- "single_word": false,
897
- "special": true
898
- },
899
- "128112": {
900
- "content": "<|reserved_special_token_107|>",
901
- "lstrip": false,
902
- "normalized": false,
903
- "rstrip": false,
904
- "single_word": false,
905
- "special": true
906
- },
907
- "128113": {
908
- "content": "<|reserved_special_token_108|>",
909
- "lstrip": false,
910
- "normalized": false,
911
- "rstrip": false,
912
- "single_word": false,
913
- "special": true
914
- },
915
- "128114": {
916
- "content": "<|reserved_special_token_109|>",
917
- "lstrip": false,
918
- "normalized": false,
919
- "rstrip": false,
920
- "single_word": false,
921
- "special": true
922
- },
923
- "128115": {
924
- "content": "<|reserved_special_token_110|>",
925
- "lstrip": false,
926
- "normalized": false,
927
- "rstrip": false,
928
- "single_word": false,
929
- "special": true
930
- },
931
- "128116": {
932
- "content": "<|reserved_special_token_111|>",
933
- "lstrip": false,
934
- "normalized": false,
935
- "rstrip": false,
936
- "single_word": false,
937
- "special": true
938
- },
939
- "128117": {
940
- "content": "<|reserved_special_token_112|>",
941
- "lstrip": false,
942
- "normalized": false,
943
- "rstrip": false,
944
- "single_word": false,
945
- "special": true
946
- },
947
- "128118": {
948
- "content": "<|reserved_special_token_113|>",
949
- "lstrip": false,
950
- "normalized": false,
951
- "rstrip": false,
952
- "single_word": false,
953
- "special": true
954
- },
955
- "128119": {
956
- "content": "<|reserved_special_token_114|>",
957
- "lstrip": false,
958
- "normalized": false,
959
- "rstrip": false,
960
- "single_word": false,
961
- "special": true
962
- },
963
- "128120": {
964
- "content": "<|reserved_special_token_115|>",
965
- "lstrip": false,
966
- "normalized": false,
967
- "rstrip": false,
968
- "single_word": false,
969
- "special": true
970
- },
971
- "128121": {
972
- "content": "<|reserved_special_token_116|>",
973
- "lstrip": false,
974
- "normalized": false,
975
- "rstrip": false,
976
- "single_word": false,
977
- "special": true
978
- },
979
- "128122": {
980
- "content": "<|reserved_special_token_117|>",
981
- "lstrip": false,
982
- "normalized": false,
983
- "rstrip": false,
984
- "single_word": false,
985
- "special": true
986
- },
987
- "128123": {
988
- "content": "<|reserved_special_token_118|>",
989
- "lstrip": false,
990
- "normalized": false,
991
- "rstrip": false,
992
- "single_word": false,
993
- "special": true
994
- },
995
- "128124": {
996
- "content": "<|reserved_special_token_119|>",
997
- "lstrip": false,
998
- "normalized": false,
999
- "rstrip": false,
1000
- "single_word": false,
1001
- "special": true
1002
- },
1003
- "128125": {
1004
- "content": "<|reserved_special_token_120|>",
1005
- "lstrip": false,
1006
- "normalized": false,
1007
- "rstrip": false,
1008
- "single_word": false,
1009
- "special": true
1010
- },
1011
- "128126": {
1012
- "content": "<|reserved_special_token_121|>",
1013
- "lstrip": false,
1014
- "normalized": false,
1015
- "rstrip": false,
1016
- "single_word": false,
1017
- "special": true
1018
- },
1019
- "128127": {
1020
- "content": "<|reserved_special_token_122|>",
1021
- "lstrip": false,
1022
- "normalized": false,
1023
- "rstrip": false,
1024
- "single_word": false,
1025
- "special": true
1026
- },
1027
- "128128": {
1028
- "content": "<|reserved_special_token_123|>",
1029
- "lstrip": false,
1030
- "normalized": false,
1031
- "rstrip": false,
1032
- "single_word": false,
1033
- "special": true
1034
- },
1035
- "128129": {
1036
- "content": "<|reserved_special_token_124|>",
1037
- "lstrip": false,
1038
- "normalized": false,
1039
- "rstrip": false,
1040
- "single_word": false,
1041
- "special": true
1042
- },
1043
- "128130": {
1044
- "content": "<|reserved_special_token_125|>",
1045
- "lstrip": false,
1046
- "normalized": false,
1047
- "rstrip": false,
1048
- "single_word": false,
1049
- "special": true
1050
- },
1051
- "128131": {
1052
- "content": "<|reserved_special_token_126|>",
1053
- "lstrip": false,
1054
- "normalized": false,
1055
- "rstrip": false,
1056
- "single_word": false,
1057
- "special": true
1058
- },
1059
- "128132": {
1060
- "content": "<|reserved_special_token_127|>",
1061
- "lstrip": false,
1062
- "normalized": false,
1063
- "rstrip": false,
1064
- "single_word": false,
1065
- "special": true
1066
- },
1067
- "128133": {
1068
- "content": "<|reserved_special_token_128|>",
1069
- "lstrip": false,
1070
- "normalized": false,
1071
- "rstrip": false,
1072
- "single_word": false,
1073
- "special": true
1074
- },
1075
- "128134": {
1076
- "content": "<|reserved_special_token_129|>",
1077
- "lstrip": false,
1078
- "normalized": false,
1079
- "rstrip": false,
1080
- "single_word": false,
1081
- "special": true
1082
- },
1083
- "128135": {
1084
- "content": "<|reserved_special_token_130|>",
1085
- "lstrip": false,
1086
- "normalized": false,
1087
- "rstrip": false,
1088
- "single_word": false,
1089
- "special": true
1090
- },
1091
- "128136": {
1092
- "content": "<|reserved_special_token_131|>",
1093
- "lstrip": false,
1094
- "normalized": false,
1095
- "rstrip": false,
1096
- "single_word": false,
1097
- "special": true
1098
- },
1099
- "128137": {
1100
- "content": "<|reserved_special_token_132|>",
1101
- "lstrip": false,
1102
- "normalized": false,
1103
- "rstrip": false,
1104
- "single_word": false,
1105
- "special": true
1106
- },
1107
- "128138": {
1108
- "content": "<|reserved_special_token_133|>",
1109
- "lstrip": false,
1110
- "normalized": false,
1111
- "rstrip": false,
1112
- "single_word": false,
1113
- "special": true
1114
- },
1115
- "128139": {
1116
- "content": "<|reserved_special_token_134|>",
1117
- "lstrip": false,
1118
- "normalized": false,
1119
- "rstrip": false,
1120
- "single_word": false,
1121
- "special": true
1122
- },
1123
- "128140": {
1124
- "content": "<|reserved_special_token_135|>",
1125
- "lstrip": false,
1126
- "normalized": false,
1127
- "rstrip": false,
1128
- "single_word": false,
1129
- "special": true
1130
- },
1131
- "128141": {
1132
- "content": "<|reserved_special_token_136|>",
1133
- "lstrip": false,
1134
- "normalized": false,
1135
- "rstrip": false,
1136
- "single_word": false,
1137
- "special": true
1138
- },
1139
- "128142": {
1140
- "content": "<|reserved_special_token_137|>",
1141
- "lstrip": false,
1142
- "normalized": false,
1143
- "rstrip": false,
1144
- "single_word": false,
1145
- "special": true
1146
- },
1147
- "128143": {
1148
- "content": "<|reserved_special_token_138|>",
1149
- "lstrip": false,
1150
- "normalized": false,
1151
- "rstrip": false,
1152
- "single_word": false,
1153
- "special": true
1154
- },
1155
- "128144": {
1156
- "content": "<|reserved_special_token_139|>",
1157
- "lstrip": false,
1158
- "normalized": false,
1159
- "rstrip": false,
1160
- "single_word": false,
1161
- "special": true
1162
- },
1163
- "128145": {
1164
- "content": "<|reserved_special_token_140|>",
1165
- "lstrip": false,
1166
- "normalized": false,
1167
- "rstrip": false,
1168
- "single_word": false,
1169
- "special": true
1170
- },
1171
- "128146": {
1172
- "content": "<|reserved_special_token_141|>",
1173
- "lstrip": false,
1174
- "normalized": false,
1175
- "rstrip": false,
1176
- "single_word": false,
1177
- "special": true
1178
- },
1179
- "128147": {
1180
- "content": "<|reserved_special_token_142|>",
1181
- "lstrip": false,
1182
- "normalized": false,
1183
- "rstrip": false,
1184
- "single_word": false,
1185
- "special": true
1186
- },
1187
- "128148": {
1188
- "content": "<|reserved_special_token_143|>",
1189
- "lstrip": false,
1190
- "normalized": false,
1191
- "rstrip": false,
1192
- "single_word": false,
1193
- "special": true
1194
- },
1195
- "128149": {
1196
- "content": "<|reserved_special_token_144|>",
1197
- "lstrip": false,
1198
- "normalized": false,
1199
- "rstrip": false,
1200
- "single_word": false,
1201
- "special": true
1202
- },
1203
- "128150": {
1204
- "content": "<|reserved_special_token_145|>",
1205
- "lstrip": false,
1206
- "normalized": false,
1207
- "rstrip": false,
1208
- "single_word": false,
1209
- "special": true
1210
- },
1211
- "128151": {
1212
- "content": "<|reserved_special_token_146|>",
1213
- "lstrip": false,
1214
- "normalized": false,
1215
- "rstrip": false,
1216
- "single_word": false,
1217
- "special": true
1218
- },
1219
- "128152": {
1220
- "content": "<|reserved_special_token_147|>",
1221
- "lstrip": false,
1222
- "normalized": false,
1223
- "rstrip": false,
1224
- "single_word": false,
1225
- "special": true
1226
- },
1227
- "128153": {
1228
- "content": "<|reserved_special_token_148|>",
1229
- "lstrip": false,
1230
- "normalized": false,
1231
- "rstrip": false,
1232
- "single_word": false,
1233
- "special": true
1234
- },
1235
- "128154": {
1236
- "content": "<|reserved_special_token_149|>",
1237
- "lstrip": false,
1238
- "normalized": false,
1239
- "rstrip": false,
1240
- "single_word": false,
1241
- "special": true
1242
- },
1243
- "128155": {
1244
- "content": "<|reserved_special_token_150|>",
1245
- "lstrip": false,
1246
- "normalized": false,
1247
- "rstrip": false,
1248
- "single_word": false,
1249
- "special": true
1250
- },
1251
- "128156": {
1252
- "content": "<|reserved_special_token_151|>",
1253
- "lstrip": false,
1254
- "normalized": false,
1255
- "rstrip": false,
1256
- "single_word": false,
1257
- "special": true
1258
- },
1259
- "128157": {
1260
- "content": "<|reserved_special_token_152|>",
1261
- "lstrip": false,
1262
- "normalized": false,
1263
- "rstrip": false,
1264
- "single_word": false,
1265
- "special": true
1266
- },
1267
- "128158": {
1268
- "content": "<|reserved_special_token_153|>",
1269
- "lstrip": false,
1270
- "normalized": false,
1271
- "rstrip": false,
1272
- "single_word": false,
1273
- "special": true
1274
- },
1275
- "128159": {
1276
- "content": "<|reserved_special_token_154|>",
1277
- "lstrip": false,
1278
- "normalized": false,
1279
- "rstrip": false,
1280
- "single_word": false,
1281
- "special": true
1282
- },
1283
- "128160": {
1284
- "content": "<|reserved_special_token_155|>",
1285
- "lstrip": false,
1286
- "normalized": false,
1287
- "rstrip": false,
1288
- "single_word": false,
1289
- "special": true
1290
- },
1291
- "128161": {
1292
- "content": "<|reserved_special_token_156|>",
1293
- "lstrip": false,
1294
- "normalized": false,
1295
- "rstrip": false,
1296
- "single_word": false,
1297
- "special": true
1298
- },
1299
- "128162": {
1300
- "content": "<|reserved_special_token_157|>",
1301
- "lstrip": false,
1302
- "normalized": false,
1303
- "rstrip": false,
1304
- "single_word": false,
1305
- "special": true
1306
- },
1307
- "128163": {
1308
- "content": "<|reserved_special_token_158|>",
1309
- "lstrip": false,
1310
- "normalized": false,
1311
- "rstrip": false,
1312
- "single_word": false,
1313
- "special": true
1314
- },
1315
- "128164": {
1316
- "content": "<|reserved_special_token_159|>",
1317
- "lstrip": false,
1318
- "normalized": false,
1319
- "rstrip": false,
1320
- "single_word": false,
1321
- "special": true
1322
- },
1323
- "128165": {
1324
- "content": "<|reserved_special_token_160|>",
1325
- "lstrip": false,
1326
- "normalized": false,
1327
- "rstrip": false,
1328
- "single_word": false,
1329
- "special": true
1330
- },
1331
- "128166": {
1332
- "content": "<|reserved_special_token_161|>",
1333
- "lstrip": false,
1334
- "normalized": false,
1335
- "rstrip": false,
1336
- "single_word": false,
1337
- "special": true
1338
- },
1339
- "128167": {
1340
- "content": "<|reserved_special_token_162|>",
1341
- "lstrip": false,
1342
- "normalized": false,
1343
- "rstrip": false,
1344
- "single_word": false,
1345
- "special": true
1346
- },
1347
- "128168": {
1348
- "content": "<|reserved_special_token_163|>",
1349
- "lstrip": false,
1350
- "normalized": false,
1351
- "rstrip": false,
1352
- "single_word": false,
1353
- "special": true
1354
- },
1355
- "128169": {
1356
- "content": "<|reserved_special_token_164|>",
1357
- "lstrip": false,
1358
- "normalized": false,
1359
- "rstrip": false,
1360
- "single_word": false,
1361
- "special": true
1362
- },
1363
- "128170": {
1364
- "content": "<|reserved_special_token_165|>",
1365
- "lstrip": false,
1366
- "normalized": false,
1367
- "rstrip": false,
1368
- "single_word": false,
1369
- "special": true
1370
- },
1371
- "128171": {
1372
- "content": "<|reserved_special_token_166|>",
1373
- "lstrip": false,
1374
- "normalized": false,
1375
- "rstrip": false,
1376
- "single_word": false,
1377
- "special": true
1378
- },
1379
- "128172": {
1380
- "content": "<|reserved_special_token_167|>",
1381
- "lstrip": false,
1382
- "normalized": false,
1383
- "rstrip": false,
1384
- "single_word": false,
1385
- "special": true
1386
- },
1387
- "128173": {
1388
- "content": "<|reserved_special_token_168|>",
1389
- "lstrip": false,
1390
- "normalized": false,
1391
- "rstrip": false,
1392
- "single_word": false,
1393
- "special": true
1394
- },
1395
- "128174": {
1396
- "content": "<|reserved_special_token_169|>",
1397
- "lstrip": false,
1398
- "normalized": false,
1399
- "rstrip": false,
1400
- "single_word": false,
1401
- "special": true
1402
- },
1403
- "128175": {
1404
- "content": "<|reserved_special_token_170|>",
1405
- "lstrip": false,
1406
- "normalized": false,
1407
- "rstrip": false,
1408
- "single_word": false,
1409
- "special": true
1410
- },
1411
- "128176": {
1412
- "content": "<|reserved_special_token_171|>",
1413
- "lstrip": false,
1414
- "normalized": false,
1415
- "rstrip": false,
1416
- "single_word": false,
1417
- "special": true
1418
- },
1419
- "128177": {
1420
- "content": "<|reserved_special_token_172|>",
1421
- "lstrip": false,
1422
- "normalized": false,
1423
- "rstrip": false,
1424
- "single_word": false,
1425
- "special": true
1426
- },
1427
- "128178": {
1428
- "content": "<|reserved_special_token_173|>",
1429
- "lstrip": false,
1430
- "normalized": false,
1431
- "rstrip": false,
1432
- "single_word": false,
1433
- "special": true
1434
- },
1435
- "128179": {
1436
- "content": "<|reserved_special_token_174|>",
1437
- "lstrip": false,
1438
- "normalized": false,
1439
- "rstrip": false,
1440
- "single_word": false,
1441
- "special": true
1442
- },
1443
- "128180": {
1444
- "content": "<|reserved_special_token_175|>",
1445
- "lstrip": false,
1446
- "normalized": false,
1447
- "rstrip": false,
1448
- "single_word": false,
1449
- "special": true
1450
- },
1451
- "128181": {
1452
- "content": "<|reserved_special_token_176|>",
1453
- "lstrip": false,
1454
- "normalized": false,
1455
- "rstrip": false,
1456
- "single_word": false,
1457
- "special": true
1458
- },
1459
- "128182": {
1460
- "content": "<|reserved_special_token_177|>",
1461
- "lstrip": false,
1462
- "normalized": false,
1463
- "rstrip": false,
1464
- "single_word": false,
1465
- "special": true
1466
- },
1467
- "128183": {
1468
- "content": "<|reserved_special_token_178|>",
1469
- "lstrip": false,
1470
- "normalized": false,
1471
- "rstrip": false,
1472
- "single_word": false,
1473
- "special": true
1474
- },
1475
- "128184": {
1476
- "content": "<|reserved_special_token_179|>",
1477
- "lstrip": false,
1478
- "normalized": false,
1479
- "rstrip": false,
1480
- "single_word": false,
1481
- "special": true
1482
- },
1483
- "128185": {
1484
- "content": "<|reserved_special_token_180|>",
1485
- "lstrip": false,
1486
- "normalized": false,
1487
- "rstrip": false,
1488
- "single_word": false,
1489
- "special": true
1490
- },
1491
- "128186": {
1492
- "content": "<|reserved_special_token_181|>",
1493
- "lstrip": false,
1494
- "normalized": false,
1495
- "rstrip": false,
1496
- "single_word": false,
1497
- "special": true
1498
- },
1499
- "128187": {
1500
- "content": "<|reserved_special_token_182|>",
1501
- "lstrip": false,
1502
- "normalized": false,
1503
- "rstrip": false,
1504
- "single_word": false,
1505
- "special": true
1506
- },
1507
- "128188": {
1508
- "content": "<|reserved_special_token_183|>",
1509
- "lstrip": false,
1510
- "normalized": false,
1511
- "rstrip": false,
1512
- "single_word": false,
1513
- "special": true
1514
- },
1515
- "128189": {
1516
- "content": "<|reserved_special_token_184|>",
1517
- "lstrip": false,
1518
- "normalized": false,
1519
- "rstrip": false,
1520
- "single_word": false,
1521
- "special": true
1522
- },
1523
- "128190": {
1524
- "content": "<|reserved_special_token_185|>",
1525
- "lstrip": false,
1526
- "normalized": false,
1527
- "rstrip": false,
1528
- "single_word": false,
1529
- "special": true
1530
- },
1531
- "128191": {
1532
- "content": "<|reserved_special_token_186|>",
1533
- "lstrip": false,
1534
- "normalized": false,
1535
- "rstrip": false,
1536
- "single_word": false,
1537
- "special": true
1538
- },
1539
- "128192": {
1540
- "content": "<|reserved_special_token_187|>",
1541
- "lstrip": false,
1542
- "normalized": false,
1543
- "rstrip": false,
1544
- "single_word": false,
1545
- "special": true
1546
- },
1547
- "128193": {
1548
- "content": "<|reserved_special_token_188|>",
1549
- "lstrip": false,
1550
- "normalized": false,
1551
- "rstrip": false,
1552
- "single_word": false,
1553
- "special": true
1554
- },
1555
- "128194": {
1556
- "content": "<|reserved_special_token_189|>",
1557
- "lstrip": false,
1558
- "normalized": false,
1559
- "rstrip": false,
1560
- "single_word": false,
1561
- "special": true
1562
- },
1563
- "128195": {
1564
- "content": "<|reserved_special_token_190|>",
1565
- "lstrip": false,
1566
- "normalized": false,
1567
- "rstrip": false,
1568
- "single_word": false,
1569
- "special": true
1570
- },
1571
- "128196": {
1572
- "content": "<|reserved_special_token_191|>",
1573
- "lstrip": false,
1574
- "normalized": false,
1575
- "rstrip": false,
1576
- "single_word": false,
1577
- "special": true
1578
- },
1579
- "128197": {
1580
- "content": "<|reserved_special_token_192|>",
1581
- "lstrip": false,
1582
- "normalized": false,
1583
- "rstrip": false,
1584
- "single_word": false,
1585
- "special": true
1586
- },
1587
- "128198": {
1588
- "content": "<|reserved_special_token_193|>",
1589
- "lstrip": false,
1590
- "normalized": false,
1591
- "rstrip": false,
1592
- "single_word": false,
1593
- "special": true
1594
- },
1595
- "128199": {
1596
- "content": "<|reserved_special_token_194|>",
1597
- "lstrip": false,
1598
- "normalized": false,
1599
- "rstrip": false,
1600
- "single_word": false,
1601
- "special": true
1602
- },
1603
- "128200": {
1604
- "content": "<|reserved_special_token_195|>",
1605
- "lstrip": false,
1606
- "normalized": false,
1607
- "rstrip": false,
1608
- "single_word": false,
1609
- "special": true
1610
- },
1611
- "128201": {
1612
- "content": "<|reserved_special_token_196|>",
1613
- "lstrip": false,
1614
- "normalized": false,
1615
- "rstrip": false,
1616
- "single_word": false,
1617
- "special": true
1618
- },
1619
- "128202": {
1620
- "content": "<|reserved_special_token_197|>",
1621
- "lstrip": false,
1622
- "normalized": false,
1623
- "rstrip": false,
1624
- "single_word": false,
1625
- "special": true
1626
- },
1627
- "128203": {
1628
- "content": "<|reserved_special_token_198|>",
1629
- "lstrip": false,
1630
- "normalized": false,
1631
- "rstrip": false,
1632
- "single_word": false,
1633
- "special": true
1634
- },
1635
- "128204": {
1636
- "content": "<|reserved_special_token_199|>",
1637
- "lstrip": false,
1638
- "normalized": false,
1639
- "rstrip": false,
1640
- "single_word": false,
1641
- "special": true
1642
- },
1643
- "128205": {
1644
- "content": "<|reserved_special_token_200|>",
1645
- "lstrip": false,
1646
- "normalized": false,
1647
- "rstrip": false,
1648
- "single_word": false,
1649
- "special": true
1650
- },
1651
- "128206": {
1652
- "content": "<|reserved_special_token_201|>",
1653
- "lstrip": false,
1654
- "normalized": false,
1655
- "rstrip": false,
1656
- "single_word": false,
1657
- "special": true
1658
- },
1659
- "128207": {
1660
- "content": "<|reserved_special_token_202|>",
1661
- "lstrip": false,
1662
- "normalized": false,
1663
- "rstrip": false,
1664
- "single_word": false,
1665
- "special": true
1666
- },
1667
- "128208": {
1668
- "content": "<|reserved_special_token_203|>",
1669
- "lstrip": false,
1670
- "normalized": false,
1671
- "rstrip": false,
1672
- "single_word": false,
1673
- "special": true
1674
- },
1675
- "128209": {
1676
- "content": "<|reserved_special_token_204|>",
1677
- "lstrip": false,
1678
- "normalized": false,
1679
- "rstrip": false,
1680
- "single_word": false,
1681
- "special": true
1682
- },
1683
- "128210": {
1684
- "content": "<|reserved_special_token_205|>",
1685
- "lstrip": false,
1686
- "normalized": false,
1687
- "rstrip": false,
1688
- "single_word": false,
1689
- "special": true
1690
- },
1691
- "128211": {
1692
- "content": "<|reserved_special_token_206|>",
1693
- "lstrip": false,
1694
- "normalized": false,
1695
- "rstrip": false,
1696
- "single_word": false,
1697
- "special": true
1698
- },
1699
- "128212": {
1700
- "content": "<|reserved_special_token_207|>",
1701
- "lstrip": false,
1702
- "normalized": false,
1703
- "rstrip": false,
1704
- "single_word": false,
1705
- "special": true
1706
- },
1707
- "128213": {
1708
- "content": "<|reserved_special_token_208|>",
1709
- "lstrip": false,
1710
- "normalized": false,
1711
- "rstrip": false,
1712
- "single_word": false,
1713
- "special": true
1714
- },
1715
- "128214": {
1716
- "content": "<|reserved_special_token_209|>",
1717
- "lstrip": false,
1718
- "normalized": false,
1719
- "rstrip": false,
1720
- "single_word": false,
1721
- "special": true
1722
- },
1723
- "128215": {
1724
- "content": "<|reserved_special_token_210|>",
1725
- "lstrip": false,
1726
- "normalized": false,
1727
- "rstrip": false,
1728
- "single_word": false,
1729
- "special": true
1730
- },
1731
- "128216": {
1732
- "content": "<|reserved_special_token_211|>",
1733
- "lstrip": false,
1734
- "normalized": false,
1735
- "rstrip": false,
1736
- "single_word": false,
1737
- "special": true
1738
- },
1739
- "128217": {
1740
- "content": "<|reserved_special_token_212|>",
1741
- "lstrip": false,
1742
- "normalized": false,
1743
- "rstrip": false,
1744
- "single_word": false,
1745
- "special": true
1746
- },
1747
- "128218": {
1748
- "content": "<|reserved_special_token_213|>",
1749
- "lstrip": false,
1750
- "normalized": false,
1751
- "rstrip": false,
1752
- "single_word": false,
1753
- "special": true
1754
- },
1755
- "128219": {
1756
- "content": "<|reserved_special_token_214|>",
1757
- "lstrip": false,
1758
- "normalized": false,
1759
- "rstrip": false,
1760
- "single_word": false,
1761
- "special": true
1762
- },
1763
- "128220": {
1764
- "content": "<|reserved_special_token_215|>",
1765
- "lstrip": false,
1766
- "normalized": false,
1767
- "rstrip": false,
1768
- "single_word": false,
1769
- "special": true
1770
- },
1771
- "128221": {
1772
- "content": "<|reserved_special_token_216|>",
1773
- "lstrip": false,
1774
- "normalized": false,
1775
- "rstrip": false,
1776
- "single_word": false,
1777
- "special": true
1778
- },
1779
- "128222": {
1780
- "content": "<|reserved_special_token_217|>",
1781
- "lstrip": false,
1782
- "normalized": false,
1783
- "rstrip": false,
1784
- "single_word": false,
1785
- "special": true
1786
- },
1787
- "128223": {
1788
- "content": "<|reserved_special_token_218|>",
1789
  "lstrip": false,
1790
  "normalized": false,
1791
  "rstrip": false,
1792
  "single_word": false,
1793
  "special": true
1794
  },
1795
- "128224": {
1796
- "content": "<|reserved_special_token_219|>",
1797
  "lstrip": false,
1798
  "normalized": false,
1799
  "rstrip": false,
1800
  "single_word": false,
1801
  "special": true
1802
  },
1803
- "128225": {
1804
- "content": "<|reserved_special_token_220|>",
1805
  "lstrip": false,
1806
  "normalized": false,
1807
  "rstrip": false,
1808
  "single_word": false,
1809
  "special": true
1810
  },
1811
- "128226": {
1812
- "content": "<|reserved_special_token_221|>",
1813
  "lstrip": false,
1814
  "normalized": false,
1815
  "rstrip": false,
1816
  "single_word": false,
1817
  "special": true
1818
  },
1819
- "128227": {
1820
- "content": "<|reserved_special_token_222|>",
1821
  "lstrip": false,
1822
  "normalized": false,
1823
  "rstrip": false,
1824
  "single_word": false,
1825
  "special": true
1826
  },
1827
- "128228": {
1828
- "content": "<|reserved_special_token_223|>",
1829
  "lstrip": false,
1830
  "normalized": false,
1831
  "rstrip": false,
1832
  "single_word": false,
1833
  "special": true
1834
  },
1835
- "128229": {
1836
- "content": "<|reserved_special_token_224|>",
1837
  "lstrip": false,
1838
  "normalized": false,
1839
  "rstrip": false,
1840
  "single_word": false,
1841
  "special": true
1842
  },
1843
- "128230": {
1844
- "content": "<|reserved_special_token_225|>",
1845
  "lstrip": false,
1846
  "normalized": false,
1847
  "rstrip": false,
1848
  "single_word": false,
1849
  "special": true
1850
  },
1851
- "128231": {
1852
- "content": "<|reserved_special_token_226|>",
1853
  "lstrip": false,
1854
  "normalized": false,
1855
  "rstrip": false,
1856
  "single_word": false,
1857
  "special": true
1858
  },
1859
- "128232": {
1860
- "content": "<|reserved_special_token_227|>",
1861
  "lstrip": false,
1862
  "normalized": false,
1863
  "rstrip": false,
1864
  "single_word": false,
1865
  "special": true
1866
  },
1867
- "128233": {
1868
- "content": "<|reserved_special_token_228|>",
1869
  "lstrip": false,
1870
  "normalized": false,
1871
  "rstrip": false,
1872
  "single_word": false,
1873
  "special": true
1874
  },
1875
- "128234": {
1876
- "content": "<|reserved_special_token_229|>",
1877
  "lstrip": false,
1878
  "normalized": false,
1879
  "rstrip": false,
1880
  "single_word": false,
1881
  "special": true
1882
  },
1883
- "128235": {
1884
- "content": "<|reserved_special_token_230|>",
1885
  "lstrip": false,
1886
  "normalized": false,
1887
  "rstrip": false,
1888
  "single_word": false,
1889
  "special": true
1890
  },
1891
- "128236": {
1892
- "content": "<|reserved_special_token_231|>",
1893
  "lstrip": false,
1894
  "normalized": false,
1895
  "rstrip": false,
1896
  "single_word": false,
1897
  "special": true
1898
  },
1899
- "128237": {
1900
- "content": "<|reserved_special_token_232|>",
1901
  "lstrip": false,
1902
  "normalized": false,
1903
  "rstrip": false,
1904
  "single_word": false,
1905
  "special": true
1906
  },
1907
- "128238": {
1908
- "content": "<|reserved_special_token_233|>",
1909
  "lstrip": false,
1910
  "normalized": false,
1911
  "rstrip": false,
1912
  "single_word": false,
1913
  "special": true
1914
  },
1915
- "128239": {
1916
- "content": "<|reserved_special_token_234|>",
1917
  "lstrip": false,
1918
  "normalized": false,
1919
  "rstrip": false,
1920
  "single_word": false,
1921
  "special": true
1922
  },
1923
- "128240": {
1924
- "content": "<|reserved_special_token_235|>",
1925
  "lstrip": false,
1926
  "normalized": false,
1927
  "rstrip": false,
1928
  "single_word": false,
1929
  "special": true
1930
  },
1931
- "128241": {
1932
- "content": "<|reserved_special_token_236|>",
1933
  "lstrip": false,
1934
  "normalized": false,
1935
  "rstrip": false,
1936
  "single_word": false,
1937
  "special": true
1938
  },
1939
- "128242": {
1940
- "content": "<|reserved_special_token_237|>",
1941
  "lstrip": false,
1942
  "normalized": false,
1943
  "rstrip": false,
1944
  "single_word": false,
1945
  "special": true
1946
  },
1947
- "128243": {
1948
- "content": "<|reserved_special_token_238|>",
1949
  "lstrip": false,
1950
  "normalized": false,
1951
  "rstrip": false,
1952
  "single_word": false,
1953
  "special": true
1954
  },
1955
- "128244": {
1956
- "content": "<|reserved_special_token_239|>",
1957
  "lstrip": false,
1958
  "normalized": false,
1959
  "rstrip": false,
1960
  "single_word": false,
1961
  "special": true
1962
  },
1963
- "128245": {
1964
- "content": "<|reserved_special_token_240|>",
1965
  "lstrip": false,
1966
  "normalized": false,
1967
  "rstrip": false,
1968
  "single_word": false,
1969
  "special": true
1970
  },
1971
- "128246": {
1972
- "content": "<|reserved_special_token_241|>",
1973
  "lstrip": false,
1974
  "normalized": false,
1975
  "rstrip": false,
1976
  "single_word": false,
1977
  "special": true
1978
  },
1979
- "128247": {
1980
- "content": "<|reserved_special_token_242|>",
1981
  "lstrip": false,
1982
  "normalized": false,
1983
  "rstrip": false,
1984
  "single_word": false,
1985
  "special": true
1986
  },
1987
- "128248": {
1988
- "content": "<|reserved_special_token_243|>",
1989
  "lstrip": false,
1990
  "normalized": false,
1991
  "rstrip": false,
1992
  "single_word": false,
1993
  "special": true
1994
  },
1995
- "128249": {
1996
- "content": "<|reserved_special_token_244|>",
1997
  "lstrip": false,
1998
  "normalized": false,
1999
  "rstrip": false,
2000
  "single_word": false,
2001
  "special": true
2002
  },
2003
- "128250": {
2004
- "content": "<|reserved_special_token_245|>",
2005
  "lstrip": false,
2006
  "normalized": false,
2007
  "rstrip": false,
2008
  "single_word": false,
2009
  "special": true
2010
  },
2011
- "128251": {
2012
- "content": "<|reserved_special_token_246|>",
2013
  "lstrip": false,
2014
  "normalized": false,
2015
  "rstrip": false,
2016
  "single_word": false,
2017
  "special": true
2018
  },
2019
- "128252": {
2020
- "content": "<|reserved_special_token_247|>",
2021
  "lstrip": false,
2022
  "normalized": false,
2023
  "rstrip": false,
2024
  "single_word": false,
2025
  "special": true
2026
  },
2027
- "128253": {
2028
- "content": "<|reserved_special_token_248|>",
2029
  "lstrip": false,
2030
  "normalized": false,
2031
  "rstrip": false,
2032
  "single_word": false,
2033
  "special": true
2034
  },
2035
- "128254": {
2036
- "content": "<|reserved_special_token_249|>",
2037
  "lstrip": false,
2038
  "normalized": false,
2039
  "rstrip": false,
2040
  "single_word": false,
2041
  "special": true
2042
  },
2043
- "128255": {
2044
- "content": "<|reserved_special_token_250|>",
2045
  "lstrip": false,
2046
  "normalized": false,
2047
  "rstrip": false,
@@ -2049,14 +274,47 @@
2049
  "special": true
2050
  }
2051
  },
2052
- "bos_token": "<|begin_of_text|>",
2053
- "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
2054
- "clean_up_tokenization_spaces": true,
2055
- "eos_token": "<|end_of_text|>",
2056
- "model_input_names": [
2057
- "input_ids",
2058
- "attention_mask"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2059
  ],
2060
- "model_max_length": 1000000000000000019884624838656,
2061
- "tokenizer_class": "PreTrainedTokenizerFast"
 
 
 
 
 
 
2062
  }
 
1
  {
2
+ "add_prefix_space": false,
3
  "added_tokens_decoder": {
4
+ "100256": {
5
+ "content": "<|reg_extra|>",
6
  "lstrip": false,
7
  "normalized": false,
8
  "rstrip": false,
9
  "single_word": false,
10
  "special": true
11
  },
12
+ "100257": {
13
+ "content": "<|endoftext|>",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
14
  "lstrip": false,
15
  "normalized": false,
16
  "rstrip": false,
17
  "single_word": false,
18
  "special": true
19
  },
20
+ "100258": {
21
+ "content": "<|fim_prefix|>",
22
  "lstrip": false,
23
  "normalized": false,
24
  "rstrip": false,
25
  "single_word": false,
26
  "special": true
27
  },
28
+ "100259": {
29
+ "content": "<|fim_middle|>",
30
  "lstrip": false,
31
  "normalized": false,
32
  "rstrip": false,
33
  "single_word": false,
34
  "special": true
35
  },
36
+ "100260": {
37
+ "content": "<|fim_suffix|>",
38
  "lstrip": false,
39
  "normalized": false,
40
  "rstrip": false,
41
  "single_word": false,
42
  "special": true
43
  },
44
+ "100261": {
45
+ "content": "<|fim_pad|>",
46
  "lstrip": false,
47
  "normalized": false,
48
  "rstrip": false,
49
  "single_word": false,
50
  "special": true
51
  },
52
+ "100262": {
53
+ "content": "<gh_stars>",
54
  "lstrip": false,
55
  "normalized": false,
56
  "rstrip": false,
57
  "single_word": false,
58
  "special": true
59
  },
60
+ "100263": {
61
+ "content": "<filename>",
62
  "lstrip": false,
63
  "normalized": false,
64
  "rstrip": false,
65
  "single_word": false,
66
  "special": true
67
  },
68
+ "100264": {
69
+ "content": "<issue_start>",
70
  "lstrip": false,
71
  "normalized": false,
72
  "rstrip": false,
73
  "single_word": false,
74
  "special": true
75
  },
76
+ "100265": {
77
+ "content": "<issue_comment>",
78
  "lstrip": false,
79
  "normalized": false,
80
  "rstrip": false,
81
  "single_word": false,
82
  "special": true
83
  },
84
+ "100266": {
85
+ "content": "<issue_closed>",
86
  "lstrip": false,
87
  "normalized": false,
88
  "rstrip": false,
89
  "single_word": false,
90
  "special": true
91
  },
92
+ "100267": {
93
+ "content": "<jupyter_start>",
94
  "lstrip": false,
95
  "normalized": false,
96
  "rstrip": false,
97
  "single_word": false,
98
  "special": true
99
  },
100
+ "100268": {
101
+ "content": "<jupyter_text>",
102
  "lstrip": false,
103
  "normalized": false,
104
  "rstrip": false,
105
  "single_word": false,
106
  "special": true
107
  },
108
+ "100269": {
109
+ "content": "<jupyter_code>",
110
  "lstrip": false,
111
  "normalized": false,
112
  "rstrip": false,
113
  "single_word": false,
114
  "special": true
115
  },
116
+ "100270": {
117
+ "content": "<jupyter_output>",
118
  "lstrip": false,
119
  "normalized": false,
120
  "rstrip": false,
121
  "single_word": false,
122
  "special": true
123
  },
124
+ "100271": {
125
+ "content": "<empty_output>",
126
  "lstrip": false,
127
  "normalized": false,
128
  "rstrip": false,
129
  "single_word": false,
130
  "special": true
131
  },
132
+ "100272": {
133
+ "content": "<commit_before>",
134
  "lstrip": false,
135
  "normalized": false,
136
  "rstrip": false,
137
  "single_word": false,
138
  "special": true
139
  },
140
+ "100273": {
141
+ "content": "<commit_msg>",
142
  "lstrip": false,
143
  "normalized": false,
144
  "rstrip": false,
145
  "single_word": false,
146
  "special": true
147
  },
148
+ "100274": {
149
+ "content": "<commit_after>",
150
  "lstrip": false,
151
  "normalized": false,
152
  "rstrip": false,
153
  "single_word": false,
154
  "special": true
155
  },
156
+ "100275": {
157
+ "content": "<reponame>",
158
  "lstrip": false,
159
  "normalized": false,
160
  "rstrip": false,
161
  "single_word": false,
162
  "special": true
163
  },
164
+ "100276": {
165
+ "content": "<|endofprompt|>",
166
  "lstrip": false,
167
  "normalized": false,
168
  "rstrip": false,
169
  "single_word": false,
170
  "special": true
171
  },
172
+ "100277": {
173
+ "content": "<|im_start|>",
174
  "lstrip": false,
175
  "normalized": false,
176
  "rstrip": false,
177
  "single_word": false,
178
  "special": true
179
  },
180
+ "100278": {
181
+ "content": "<|im_end|>",
182
  "lstrip": false,
183
  "normalized": false,
184
  "rstrip": false,
185
  "single_word": false,
186
  "special": true
187
  },
188
+ "100279": {
189
+ "content": "<|pause|>",
190
  "lstrip": false,
191
  "normalized": false,
192
  "rstrip": false,
193
  "single_word": false,
194
  "special": true
195
  },
196
+ "100280": {
197
+ "content": "<|reg0|>",
198
  "lstrip": false,
199
  "normalized": false,
200
  "rstrip": false,
201
  "single_word": false,
202
  "special": true
203
  },
204
+ "100281": {
205
+ "content": "<|reg1|>",
206
  "lstrip": false,
207
  "normalized": false,
208
  "rstrip": false,
209
  "single_word": false,
210
  "special": true
211
  },
212
+ "100282": {
213
+ "content": "<|reg2|>",
214
  "lstrip": false,
215
  "normalized": false,
216
  "rstrip": false,
217
  "single_word": false,
218
  "special": true
219
  },
220
+ "100283": {
221
+ "content": "<|reg3|>",
222
  "lstrip": false,
223
  "normalized": false,
224
  "rstrip": false,
225
  "single_word": false,
226
  "special": true
227
  },
228
+ "100284": {
229
+ "content": "<|reg4|>",
230
  "lstrip": false,
231
  "normalized": false,
232
  "rstrip": false,
233
  "single_word": false,
234
  "special": true
235
  },
236
+ "100285": {
237
+ "content": "<|reg5|>",
238
  "lstrip": false,
239
  "normalized": false,
240
  "rstrip": false,
241
  "single_word": false,
242
  "special": true
243
  },
244
+ "100286": {
245
+ "content": "<|reg6|>",
246
  "lstrip": false,
247
  "normalized": false,
248
  "rstrip": false,
249
  "single_word": false,
250
  "special": true
251
  },
252
+ "100287": {
253
+ "content": "<|reg7|>",
254
  "lstrip": false,
255
  "normalized": false,
256
  "rstrip": false,
257
  "single_word": false,
258
  "special": true
259
  },
260
+ "100288": {
261
+ "content": "<|extra0|>",
262
  "lstrip": false,
263
  "normalized": false,
264
  "rstrip": false,
265
  "single_word": false,
266
  "special": true
267
  },
268
+ "100289": {
269
+ "content": "<|end_of_text|>",
270
  "lstrip": false,
271
  "normalized": false,
272
  "rstrip": false,
 
274
  "special": true
275
  }
276
  },
277
+ "additional_special_tokens": [
278
+ "<|reg_extra|>",
279
+ "<|endoftext|>",
280
+ "<|fim_prefix|>",
281
+ "<|fim_middle|>",
282
+ "<|fim_suffix|>",
283
+ "<|fim_pad|>",
284
+ "<gh_stars>",
285
+ "<filename>",
286
+ "<issue_start>",
287
+ "<issue_comment>",
288
+ "<issue_closed>",
289
+ "<jupyter_start>",
290
+ "<jupyter_text>",
291
+ "<jupyter_code>",
292
+ "<jupyter_output>",
293
+ "<empty_output>",
294
+ "<commit_before>",
295
+ "<commit_msg>",
296
+ "<commit_after>",
297
+ "<reponame>",
298
+ "<|endofprompt|>",
299
+ "<|im_start|>",
300
+ "<|im_end|>",
301
+ "<|pause|>",
302
+ "<|reg0|>",
303
+ "<|reg1|>",
304
+ "<|reg2|>",
305
+ "<|reg3|>",
306
+ "<|reg4|>",
307
+ "<|reg5|>",
308
+ "<|reg6|>",
309
+ "<|reg7|>",
310
+ "<|extra0|>"
311
  ],
312
+ "bos_token": "<|endoftext|>",
313
+ "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
314
+ "clean_up_tokenization_spaces": true,
315
+ "eos_token": "<|endoftext|>",
316
+ "model_max_length": 2048,
317
+ "pad_token": "<|end_of_text|>",
318
+ "tokenizer_class": "GPT2Tokenizer",
319
+ "unk_token": "<|endoftext|>"
320
  }
vocab.json ADDED
The diff for this file is too large to render. See raw diff