yasserrmd commited on
Commit
a766290
·
verified ·
1 Parent(s): b605511

Upload tokenizer

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
added_tokens.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|box_end|>": 151649,
5
+ "<|box_start|>": 151648,
6
+ "<|endoftext|>": 151643,
7
+ "<|file_sep|>": 151664,
8
+ "<|fim_middle|>": 151660,
9
+ "<|fim_pad|>": 151662,
10
+ "<|fim_prefix|>": 151659,
11
+ "<|fim_suffix|>": 151661,
12
+ "<|im_end|>": 151645,
13
+ "<|im_start|>": 151644,
14
+ "<|image_pad|>": 151655,
15
+ "<|object_ref_end|>": 151647,
16
+ "<|object_ref_start|>": 151646,
17
+ "<|quad_end|>": 151651,
18
+ "<|quad_start|>": 151650,
19
+ "<|repo_name|>": 151663,
20
+ "<|video_pad|>": 151656,
21
+ "<|vision_end|>": 151653,
22
+ "<|vision_pad|>": 151654,
23
+ "<|vision_start|>": 151652
24
+ }
merges.txt CHANGED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json CHANGED
@@ -1,27 +1,28 @@
1
  {
2
- "bos_token": {
3
- "content": "<|endoftext|>",
4
- "lstrip": true,
5
- "normalized": false,
6
- "rstrip": true,
7
- "single_word": false
8
- },
 
 
 
 
 
 
 
 
9
  "eos_token": {
10
  "content": "<|im_end|>",
11
- "lstrip": true,
12
  "normalized": false,
13
- "rstrip": true,
14
  "single_word": false
15
  },
16
  "pad_token": {
17
- "content": "<|dummy_87|>",
18
- "lstrip": true,
19
- "normalized": false,
20
- "rstrip": true,
21
- "single_word": false
22
- },
23
- "unk_token": {
24
- "content": "�",
25
  "lstrip": false,
26
  "normalized": false,
27
  "rstrip": false,
 
1
  {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
  "eos_token": {
18
  "content": "<|im_end|>",
19
+ "lstrip": false,
20
  "normalized": false,
21
+ "rstrip": false,
22
  "single_word": false
23
  },
24
  "pad_token": {
25
+ "content": "<|vision_pad|>",
 
 
 
 
 
 
 
26
  "lstrip": false,
27
  "normalized": false,
28
  "rstrip": false,
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,791 +1,209 @@
1
  {
 
2
  "add_prefix_space": false,
3
  "added_tokens_decoder": {
4
- "5809": {
5
- "content": "�",
6
  "lstrip": false,
7
  "normalized": false,
8
  "rstrip": false,
9
  "single_word": false,
10
  "special": true
11
  },
12
- "100256": {
13
- "content": "<|dummy_0|>",
14
- "lstrip": true,
15
- "normalized": false,
16
- "rstrip": true,
17
- "single_word": false,
18
- "special": true
19
- },
20
- "100257": {
21
- "content": "<|endoftext|>",
22
- "lstrip": true,
23
- "normalized": false,
24
- "rstrip": true,
25
- "single_word": false,
26
- "special": true
27
- },
28
- "100258": {
29
- "content": "<|fim_prefix|>",
30
- "lstrip": true,
31
- "normalized": false,
32
- "rstrip": true,
33
- "single_word": false,
34
- "special": true
35
- },
36
- "100259": {
37
- "content": "<|fim_middle|>",
38
- "lstrip": true,
39
- "normalized": false,
40
- "rstrip": true,
41
- "single_word": false,
42
- "special": true
43
- },
44
- "100260": {
45
- "content": "<|fim_suffix|>",
46
- "lstrip": true,
47
- "normalized": false,
48
- "rstrip": true,
49
- "single_word": false,
50
- "special": true
51
- },
52
- "100261": {
53
- "content": "<|dummy_1|>",
54
- "lstrip": true,
55
- "normalized": false,
56
- "rstrip": true,
57
- "single_word": false,
58
- "special": true
59
- },
60
- "100262": {
61
- "content": "<|dummy_2|>",
62
- "lstrip": true,
63
- "normalized": false,
64
- "rstrip": true,
65
- "single_word": false,
66
- "special": true
67
- },
68
- "100263": {
69
- "content": "<|dummy_3|>",
70
- "lstrip": true,
71
- "normalized": false,
72
- "rstrip": true,
73
- "single_word": false,
74
- "special": true
75
- },
76
- "100264": {
77
  "content": "<|im_start|>",
78
- "lstrip": true,
79
  "normalized": false,
80
- "rstrip": true,
81
  "single_word": false,
82
  "special": true
83
  },
84
- "100265": {
85
  "content": "<|im_end|>",
86
- "lstrip": true,
87
- "normalized": false,
88
- "rstrip": true,
89
- "single_word": false,
90
- "special": true
91
- },
92
- "100266": {
93
- "content": "<|im_sep|>",
94
- "lstrip": true,
95
- "normalized": false,
96
- "rstrip": true,
97
- "single_word": false,
98
- "special": true
99
- },
100
- "100267": {
101
- "content": "<|dummy_4|>",
102
- "lstrip": true,
103
- "normalized": false,
104
- "rstrip": true,
105
- "single_word": false,
106
- "special": true
107
- },
108
- "100268": {
109
- "content": "<|dummy_5|>",
110
- "lstrip": true,
111
- "normalized": false,
112
- "rstrip": true,
113
- "single_word": false,
114
- "special": true
115
- },
116
- "100269": {
117
- "content": "<|dummy_6|>",
118
- "lstrip": true,
119
- "normalized": false,
120
- "rstrip": true,
121
- "single_word": false,
122
- "special": true
123
- },
124
- "100270": {
125
- "content": "<|dummy_7|>",
126
- "lstrip": true,
127
- "normalized": false,
128
- "rstrip": true,
129
- "single_word": false,
130
- "special": true
131
- },
132
- "100271": {
133
- "content": "<|dummy_8|>",
134
- "lstrip": true,
135
- "normalized": false,
136
- "rstrip": true,
137
- "single_word": false,
138
- "special": true
139
- },
140
- "100272": {
141
- "content": "<|dummy_9|>",
142
- "lstrip": true,
143
- "normalized": false,
144
- "rstrip": true,
145
- "single_word": false,
146
- "special": true
147
- },
148
- "100273": {
149
- "content": "<|dummy_10|>",
150
- "lstrip": true,
151
- "normalized": false,
152
- "rstrip": true,
153
- "single_word": false,
154
- "special": true
155
- },
156
- "100274": {
157
- "content": "<|dummy_11|>",
158
- "lstrip": true,
159
- "normalized": false,
160
- "rstrip": true,
161
- "single_word": false,
162
- "special": true
163
- },
164
- "100275": {
165
- "content": "<|dummy_12|>",
166
- "lstrip": true,
167
- "normalized": false,
168
- "rstrip": true,
169
- "single_word": false,
170
- "special": true
171
- },
172
- "100276": {
173
- "content": "<|endofprompt|>",
174
- "lstrip": true,
175
- "normalized": false,
176
- "rstrip": true,
177
- "single_word": false,
178
- "special": true
179
- },
180
- "100277": {
181
- "content": "<|dummy_13|>",
182
- "lstrip": true,
183
- "normalized": false,
184
- "rstrip": true,
185
- "single_word": false,
186
- "special": true
187
- },
188
- "100278": {
189
- "content": "<|dummy_14|>",
190
- "lstrip": true,
191
- "normalized": false,
192
- "rstrip": true,
193
- "single_word": false,
194
- "special": true
195
- },
196
- "100279": {
197
- "content": "<|dummy_15|>",
198
- "lstrip": true,
199
- "normalized": false,
200
- "rstrip": true,
201
- "single_word": false,
202
- "special": true
203
- },
204
- "100280": {
205
- "content": "<|dummy_16|>",
206
- "lstrip": true,
207
- "normalized": false,
208
- "rstrip": true,
209
- "single_word": false,
210
- "special": true
211
- },
212
- "100281": {
213
- "content": "<|dummy_17|>",
214
- "lstrip": true,
215
- "normalized": false,
216
- "rstrip": true,
217
- "single_word": false,
218
- "special": true
219
- },
220
- "100282": {
221
- "content": "<|dummy_18|>",
222
- "lstrip": true,
223
- "normalized": false,
224
- "rstrip": true,
225
- "single_word": false,
226
- "special": true
227
- },
228
- "100283": {
229
- "content": "<|dummy_19|>",
230
- "lstrip": true,
231
- "normalized": false,
232
- "rstrip": true,
233
- "single_word": false,
234
- "special": true
235
- },
236
- "100284": {
237
- "content": "<|dummy_20|>",
238
- "lstrip": true,
239
- "normalized": false,
240
- "rstrip": true,
241
- "single_word": false,
242
- "special": true
243
- },
244
- "100285": {
245
- "content": "<|dummy_21|>",
246
- "lstrip": true,
247
- "normalized": false,
248
- "rstrip": true,
249
- "single_word": false,
250
- "special": true
251
- },
252
- "100286": {
253
- "content": "<|dummy_22|>",
254
- "lstrip": true,
255
- "normalized": false,
256
- "rstrip": true,
257
- "single_word": false,
258
- "special": true
259
- },
260
- "100287": {
261
- "content": "<|dummy_23|>",
262
- "lstrip": true,
263
- "normalized": false,
264
- "rstrip": true,
265
- "single_word": false,
266
- "special": true
267
- },
268
- "100288": {
269
- "content": "<|dummy_24|>",
270
- "lstrip": true,
271
- "normalized": false,
272
- "rstrip": true,
273
- "single_word": false,
274
- "special": true
275
- },
276
- "100289": {
277
- "content": "<|dummy_25|>",
278
- "lstrip": true,
279
- "normalized": false,
280
- "rstrip": true,
281
- "single_word": false,
282
- "special": true
283
- },
284
- "100290": {
285
- "content": "<|dummy_26|>",
286
- "lstrip": true,
287
- "normalized": false,
288
- "rstrip": true,
289
- "single_word": false,
290
- "special": true
291
- },
292
- "100291": {
293
- "content": "<|dummy_27|>",
294
- "lstrip": true,
295
- "normalized": false,
296
- "rstrip": true,
297
- "single_word": false,
298
- "special": true
299
- },
300
- "100292": {
301
- "content": "<|dummy_28|>",
302
- "lstrip": true,
303
- "normalized": false,
304
- "rstrip": true,
305
- "single_word": false,
306
- "special": true
307
- },
308
- "100293": {
309
- "content": "<|dummy_29|>",
310
- "lstrip": true,
311
- "normalized": false,
312
- "rstrip": true,
313
- "single_word": false,
314
- "special": true
315
- },
316
- "100294": {
317
- "content": "<|dummy_30|>",
318
- "lstrip": true,
319
- "normalized": false,
320
- "rstrip": true,
321
- "single_word": false,
322
- "special": true
323
- },
324
- "100295": {
325
- "content": "<|dummy_31|>",
326
- "lstrip": true,
327
- "normalized": false,
328
- "rstrip": true,
329
- "single_word": false,
330
- "special": true
331
- },
332
- "100296": {
333
- "content": "<|dummy_32|>",
334
- "lstrip": true,
335
- "normalized": false,
336
- "rstrip": true,
337
- "single_word": false,
338
- "special": true
339
- },
340
- "100297": {
341
- "content": "<|dummy_33|>",
342
- "lstrip": true,
343
- "normalized": false,
344
- "rstrip": true,
345
- "single_word": false,
346
- "special": true
347
- },
348
- "100298": {
349
- "content": "<|dummy_34|>",
350
- "lstrip": true,
351
- "normalized": false,
352
- "rstrip": true,
353
- "single_word": false,
354
- "special": true
355
- },
356
- "100299": {
357
- "content": "<|dummy_35|>",
358
- "lstrip": true,
359
- "normalized": false,
360
- "rstrip": true,
361
- "single_word": false,
362
- "special": true
363
- },
364
- "100300": {
365
- "content": "<|dummy_36|>",
366
- "lstrip": true,
367
- "normalized": false,
368
- "rstrip": true,
369
- "single_word": false,
370
- "special": true
371
- },
372
- "100301": {
373
- "content": "<|dummy_37|>",
374
- "lstrip": true,
375
- "normalized": false,
376
- "rstrip": true,
377
- "single_word": false,
378
- "special": true
379
- },
380
- "100302": {
381
- "content": "<|dummy_38|>",
382
- "lstrip": true,
383
- "normalized": false,
384
- "rstrip": true,
385
- "single_word": false,
386
- "special": true
387
- },
388
- "100303": {
389
- "content": "<|dummy_39|>",
390
- "lstrip": true,
391
- "normalized": false,
392
- "rstrip": true,
393
- "single_word": false,
394
- "special": true
395
- },
396
- "100304": {
397
- "content": "<|dummy_40|>",
398
- "lstrip": true,
399
- "normalized": false,
400
- "rstrip": true,
401
- "single_word": false,
402
- "special": true
403
- },
404
- "100305": {
405
- "content": "<|dummy_41|>",
406
- "lstrip": true,
407
- "normalized": false,
408
- "rstrip": true,
409
- "single_word": false,
410
- "special": true
411
- },
412
- "100306": {
413
- "content": "<|dummy_42|>",
414
- "lstrip": true,
415
- "normalized": false,
416
- "rstrip": true,
417
- "single_word": false,
418
- "special": true
419
- },
420
- "100307": {
421
- "content": "<|dummy_43|>",
422
- "lstrip": true,
423
- "normalized": false,
424
- "rstrip": true,
425
- "single_word": false,
426
- "special": true
427
- },
428
- "100308": {
429
- "content": "<|dummy_44|>",
430
- "lstrip": true,
431
- "normalized": false,
432
- "rstrip": true,
433
- "single_word": false,
434
- "special": true
435
- },
436
- "100309": {
437
- "content": "<|dummy_45|>",
438
- "lstrip": true,
439
- "normalized": false,
440
- "rstrip": true,
441
- "single_word": false,
442
- "special": true
443
- },
444
- "100310": {
445
- "content": "<|dummy_46|>",
446
- "lstrip": true,
447
- "normalized": false,
448
- "rstrip": true,
449
- "single_word": false,
450
- "special": true
451
- },
452
- "100311": {
453
- "content": "<|dummy_47|>",
454
- "lstrip": true,
455
- "normalized": false,
456
- "rstrip": true,
457
- "single_word": false,
458
- "special": true
459
- },
460
- "100312": {
461
- "content": "<|dummy_48|>",
462
- "lstrip": true,
463
- "normalized": false,
464
- "rstrip": true,
465
- "single_word": false,
466
- "special": true
467
- },
468
- "100313": {
469
- "content": "<|dummy_49|>",
470
- "lstrip": true,
471
- "normalized": false,
472
- "rstrip": true,
473
- "single_word": false,
474
- "special": true
475
- },
476
- "100314": {
477
- "content": "<|dummy_50|>",
478
- "lstrip": true,
479
- "normalized": false,
480
- "rstrip": true,
481
- "single_word": false,
482
- "special": true
483
- },
484
- "100315": {
485
- "content": "<|dummy_51|>",
486
- "lstrip": true,
487
- "normalized": false,
488
- "rstrip": true,
489
- "single_word": false,
490
- "special": true
491
- },
492
- "100316": {
493
- "content": "<|dummy_52|>",
494
- "lstrip": true,
495
- "normalized": false,
496
- "rstrip": true,
497
- "single_word": false,
498
- "special": true
499
- },
500
- "100317": {
501
- "content": "<|dummy_53|>",
502
- "lstrip": true,
503
- "normalized": false,
504
- "rstrip": true,
505
- "single_word": false,
506
- "special": true
507
- },
508
- "100318": {
509
- "content": "<|dummy_54|>",
510
- "lstrip": true,
511
- "normalized": false,
512
- "rstrip": true,
513
- "single_word": false,
514
- "special": true
515
- },
516
- "100319": {
517
- "content": "<|dummy_55|>",
518
- "lstrip": true,
519
- "normalized": false,
520
- "rstrip": true,
521
- "single_word": false,
522
- "special": true
523
- },
524
- "100320": {
525
- "content": "<|dummy_56|>",
526
- "lstrip": true,
527
- "normalized": false,
528
- "rstrip": true,
529
- "single_word": false,
530
- "special": true
531
- },
532
- "100321": {
533
- "content": "<|dummy_57|>",
534
- "lstrip": true,
535
- "normalized": false,
536
- "rstrip": true,
537
- "single_word": false,
538
- "special": true
539
- },
540
- "100322": {
541
- "content": "<|dummy_58|>",
542
- "lstrip": true,
543
- "normalized": false,
544
- "rstrip": true,
545
- "single_word": false,
546
- "special": true
547
- },
548
- "100323": {
549
- "content": "<|dummy_59|>",
550
- "lstrip": true,
551
- "normalized": false,
552
- "rstrip": true,
553
- "single_word": false,
554
- "special": true
555
- },
556
- "100324": {
557
- "content": "<|dummy_60|>",
558
- "lstrip": true,
559
- "normalized": false,
560
- "rstrip": true,
561
- "single_word": false,
562
- "special": true
563
- },
564
- "100325": {
565
- "content": "<|dummy_61|>",
566
- "lstrip": true,
567
- "normalized": false,
568
- "rstrip": true,
569
- "single_word": false,
570
- "special": true
571
- },
572
- "100326": {
573
- "content": "<|dummy_62|>",
574
- "lstrip": true,
575
- "normalized": false,
576
- "rstrip": true,
577
- "single_word": false,
578
- "special": true
579
- },
580
- "100327": {
581
- "content": "<|dummy_63|>",
582
- "lstrip": true,
583
- "normalized": false,
584
- "rstrip": true,
585
- "single_word": false,
586
- "special": true
587
- },
588
- "100328": {
589
- "content": "<|dummy_64|>",
590
- "lstrip": true,
591
- "normalized": false,
592
- "rstrip": true,
593
- "single_word": false,
594
- "special": true
595
- },
596
- "100329": {
597
- "content": "<|dummy_65|>",
598
- "lstrip": true,
599
- "normalized": false,
600
- "rstrip": true,
601
- "single_word": false,
602
- "special": true
603
- },
604
- "100330": {
605
- "content": "<|dummy_66|>",
606
- "lstrip": true,
607
- "normalized": false,
608
- "rstrip": true,
609
- "single_word": false,
610
- "special": true
611
- },
612
- "100331": {
613
- "content": "<|dummy_67|>",
614
- "lstrip": true,
615
- "normalized": false,
616
- "rstrip": true,
617
- "single_word": false,
618
- "special": true
619
- },
620
- "100332": {
621
- "content": "<|dummy_68|>",
622
- "lstrip": true,
623
  "normalized": false,
624
- "rstrip": true,
625
  "single_word": false,
626
  "special": true
627
  },
628
- "100333": {
629
- "content": "<|dummy_69|>",
630
- "lstrip": true,
631
  "normalized": false,
632
- "rstrip": true,
633
  "single_word": false,
634
  "special": true
635
  },
636
- "100334": {
637
- "content": "<|dummy_70|>",
638
- "lstrip": true,
639
  "normalized": false,
640
- "rstrip": true,
641
  "single_word": false,
642
  "special": true
643
  },
644
- "100335": {
645
- "content": "<|dummy_71|>",
646
- "lstrip": true,
647
  "normalized": false,
648
- "rstrip": true,
649
  "single_word": false,
650
  "special": true
651
  },
652
- "100336": {
653
- "content": "<|dummy_72|>",
654
- "lstrip": true,
655
  "normalized": false,
656
- "rstrip": true,
657
  "single_word": false,
658
  "special": true
659
  },
660
- "100337": {
661
- "content": "<|dummy_73|>",
662
- "lstrip": true,
663
  "normalized": false,
664
- "rstrip": true,
665
  "single_word": false,
666
  "special": true
667
  },
668
- "100338": {
669
- "content": "<|dummy_74|>",
670
- "lstrip": true,
671
  "normalized": false,
672
- "rstrip": true,
673
  "single_word": false,
674
  "special": true
675
  },
676
- "100339": {
677
- "content": "<|dummy_75|>",
678
- "lstrip": true,
679
  "normalized": false,
680
- "rstrip": true,
681
  "single_word": false,
682
  "special": true
683
  },
684
- "100340": {
685
- "content": "<|dummy_76|>",
686
- "lstrip": true,
687
  "normalized": false,
688
- "rstrip": true,
689
  "single_word": false,
690
  "special": true
691
  },
692
- "100341": {
693
- "content": "<|dummy_77|>",
694
- "lstrip": true,
695
  "normalized": false,
696
- "rstrip": true,
697
  "single_word": false,
698
  "special": true
699
  },
700
- "100342": {
701
- "content": "<|dummy_78|>",
702
- "lstrip": true,
703
  "normalized": false,
704
- "rstrip": true,
705
  "single_word": false,
706
  "special": true
707
  },
708
- "100343": {
709
- "content": "<|dummy_79|>",
710
- "lstrip": true,
711
  "normalized": false,
712
- "rstrip": true,
713
  "single_word": false,
714
  "special": true
715
  },
716
- "100344": {
717
- "content": "<|dummy_80|>",
718
- "lstrip": true,
719
  "normalized": false,
720
- "rstrip": true,
721
  "single_word": false,
722
- "special": true
723
  },
724
- "100345": {
725
- "content": "<|dummy_81|>",
726
- "lstrip": true,
727
  "normalized": false,
728
- "rstrip": true,
729
  "single_word": false,
730
- "special": true
731
  },
732
- "100346": {
733
- "content": "<|dummy_82|>",
734
- "lstrip": true,
735
  "normalized": false,
736
- "rstrip": true,
737
  "single_word": false,
738
- "special": true
739
  },
740
- "100347": {
741
- "content": "<|dummy_83|>",
742
- "lstrip": true,
743
  "normalized": false,
744
- "rstrip": true,
745
  "single_word": false,
746
- "special": true
747
  },
748
- "100348": {
749
- "content": "<|dummy_84|>",
750
- "lstrip": true,
751
  "normalized": false,
752
- "rstrip": true,
753
  "single_word": false,
754
- "special": true
755
  },
756
- "100349": {
757
- "content": "<|dummy_85|>",
758
- "lstrip": true,
759
  "normalized": false,
760
- "rstrip": true,
761
  "single_word": false,
762
- "special": true
763
  },
764
- "100350": {
765
- "content": "<|dummy_86|>",
766
- "lstrip": true,
767
  "normalized": false,
768
- "rstrip": true,
769
  "single_word": false,
770
- "special": true
771
  },
772
- "100351": {
773
- "content": "<|dummy_87|>",
774
- "lstrip": true,
775
  "normalized": false,
776
- "rstrip": true,
777
  "single_word": false,
778
- "special": true
779
  }
780
  },
781
- "bos_token": "<|endoftext|>",
782
- "chat_template": "{% for message in messages %}{% if (message['role'] == 'system') %}{{'<|im_start|>system<|im_sep|>' + message['content'] + '<|im_end|>'}}{% elif (message['role'] == 'user') %}{{'<|im_start|>user<|im_sep|>' + message['content'] + '<|im_end|>'}}{% elif (message['role'] == 'assistant') %}{{'<|im_start|>assistant<|im_sep|>' + message['content'] + '<|im_end|>'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant<|im_sep|>' }}{% endif %}",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
783
  "clean_up_tokenization_spaces": false,
784
  "eos_token": "<|im_end|>",
 
785
  "extra_special_tokens": {},
786
- "model_max_length": 16384,
787
- "pad_token": "<|dummy_87|>",
788
  "padding_side": "left",
789
- "tokenizer_class": "GPT2Tokenizer",
790
- "unk_token": "�"
 
791
  }
 
1
  {
2
+ "add_bos_token": false,
3
  "add_prefix_space": false,
4
  "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
  "lstrip": false,
8
  "normalized": false,
9
  "rstrip": false,
10
  "single_word": false,
11
  "special": true
12
  },
13
+ "151644": {
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
14
  "content": "<|im_start|>",
15
+ "lstrip": false,
16
  "normalized": false,
17
+ "rstrip": false,
18
  "single_word": false,
19
  "special": true
20
  },
21
+ "151645": {
22
  "content": "<|im_end|>",
23
+ "lstrip": false,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
24
  "normalized": false,
25
+ "rstrip": false,
26
  "single_word": false,
27
  "special": true
28
  },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
  "normalized": false,
33
+ "rstrip": false,
34
  "single_word": false,
35
  "special": true
36
  },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
  "normalized": false,
41
+ "rstrip": false,
42
  "single_word": false,
43
  "special": true
44
  },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
  "normalized": false,
49
+ "rstrip": false,
50
  "single_word": false,
51
  "special": true
52
  },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
  "normalized": false,
57
+ "rstrip": false,
58
  "single_word": false,
59
  "special": true
60
  },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
  "normalized": false,
65
+ "rstrip": false,
66
  "single_word": false,
67
  "special": true
68
  },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
  "normalized": false,
73
+ "rstrip": false,
74
  "single_word": false,
75
  "special": true
76
  },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
  "normalized": false,
81
+ "rstrip": false,
82
  "single_word": false,
83
  "special": true
84
  },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
  "normalized": false,
89
+ "rstrip": false,
90
  "single_word": false,
91
  "special": true
92
  },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
  "normalized": false,
97
+ "rstrip": false,
98
  "single_word": false,
99
  "special": true
100
  },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
  "normalized": false,
105
+ "rstrip": false,
106
  "single_word": false,
107
  "special": true
108
  },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
  "normalized": false,
113
+ "rstrip": false,
114
  "single_word": false,
115
  "special": true
116
  },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
  "normalized": false,
121
+ "rstrip": false,
122
  "single_word": false,
123
+ "special": false
124
  },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
  "normalized": false,
129
+ "rstrip": false,
130
  "single_word": false,
131
+ "special": false
132
  },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
  "normalized": false,
137
+ "rstrip": false,
138
  "single_word": false,
139
+ "special": false
140
  },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
  "normalized": false,
145
+ "rstrip": false,
146
  "single_word": false,
147
+ "special": false
148
  },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
  "normalized": false,
153
+ "rstrip": false,
154
  "single_word": false,
155
+ "special": false
156
  },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
  "normalized": false,
161
+ "rstrip": false,
162
  "single_word": false,
163
+ "special": false
164
  },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
  "normalized": false,
169
+ "rstrip": false,
170
  "single_word": false,
171
+ "special": false
172
  },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
  "normalized": false,
177
+ "rstrip": false,
178
  "single_word": false,
179
+ "special": false
180
  }
181
  },
182
+ "additional_special_tokens": [
183
+ "<|im_start|>",
184
+ "<|im_end|>",
185
+ "<|object_ref_start|>",
186
+ "<|object_ref_end|>",
187
+ "<|box_start|>",
188
+ "<|box_end|>",
189
+ "<|quad_start|>",
190
+ "<|quad_end|>",
191
+ "<|vision_start|>",
192
+ "<|vision_end|>",
193
+ "<|vision_pad|>",
194
+ "<|image_pad|>",
195
+ "<|video_pad|>"
196
+ ],
197
+ "bos_token": null,
198
+ "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
199
  "clean_up_tokenization_spaces": false,
200
  "eos_token": "<|im_end|>",
201
+ "errors": "replace",
202
  "extra_special_tokens": {},
203
+ "model_max_length": 32768,
204
+ "pad_token": "<|vision_pad|>",
205
  "padding_side": "left",
206
+ "split_special_tokens": false,
207
+ "tokenizer_class": "Qwen2Tokenizer",
208
+ "unk_token": null
209
  }
vocab.json CHANGED
The diff for this file is too large to render. See raw diff