jan-hq commited on
Commit
ac55a68
·
verified ·
1 Parent(s): 8af3d87

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
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin▁of▁sentence|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|end▁of▁sentence|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|vision_pad|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8730126b34dd527064a803e9311c9fa8264761937c503493b8c05599cf8edd3c
3
+ size 11431945
tokenizer_config.json ADDED
@@ -0,0 +1,584 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": null,
5
+ "added_tokens_decoder": {
6
+ "151643": {
7
+ "content": "<|end▁of▁sentence|>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "151644": {
15
+ "content": "<|User|>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": false
21
+ },
22
+ "151645": {
23
+ "content": "<|Assistant|>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": false
29
+ },
30
+ "151646": {
31
+ "content": "<|begin▁of▁sentence|>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "151647": {
39
+ "content": "<|EOT|>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false,
44
+ "special": false
45
+ },
46
+ "151648": {
47
+ "content": "<think>",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": false,
51
+ "single_word": false,
52
+ "special": false
53
+ },
54
+ "151649": {
55
+ "content": "</think>",
56
+ "lstrip": false,
57
+ "normalized": false,
58
+ "rstrip": false,
59
+ "single_word": false,
60
+ "special": false
61
+ },
62
+ "151650": {
63
+ "content": "<|quad_start|>",
64
+ "lstrip": false,
65
+ "normalized": false,
66
+ "rstrip": false,
67
+ "single_word": false,
68
+ "special": true
69
+ },
70
+ "151651": {
71
+ "content": "<|quad_end|>",
72
+ "lstrip": false,
73
+ "normalized": false,
74
+ "rstrip": false,
75
+ "single_word": false,
76
+ "special": true
77
+ },
78
+ "151652": {
79
+ "content": "<|vision_start|>",
80
+ "lstrip": false,
81
+ "normalized": false,
82
+ "rstrip": false,
83
+ "single_word": false,
84
+ "special": true
85
+ },
86
+ "151653": {
87
+ "content": "<|vision_end|>",
88
+ "lstrip": false,
89
+ "normalized": false,
90
+ "rstrip": false,
91
+ "single_word": false,
92
+ "special": true
93
+ },
94
+ "151654": {
95
+ "content": "<|vision_pad|>",
96
+ "lstrip": false,
97
+ "normalized": false,
98
+ "rstrip": false,
99
+ "single_word": false,
100
+ "special": true
101
+ },
102
+ "151655": {
103
+ "content": "<|image_pad|>",
104
+ "lstrip": false,
105
+ "normalized": false,
106
+ "rstrip": false,
107
+ "single_word": false,
108
+ "special": true
109
+ },
110
+ "151656": {
111
+ "content": "<|video_pad|>",
112
+ "lstrip": false,
113
+ "normalized": false,
114
+ "rstrip": false,
115
+ "single_word": false,
116
+ "special": true
117
+ },
118
+ "151657": {
119
+ "content": "<tool_call>",
120
+ "lstrip": false,
121
+ "normalized": false,
122
+ "rstrip": false,
123
+ "single_word": false,
124
+ "special": false
125
+ },
126
+ "151658": {
127
+ "content": "</tool_call>",
128
+ "lstrip": false,
129
+ "normalized": false,
130
+ "rstrip": false,
131
+ "single_word": false,
132
+ "special": false
133
+ },
134
+ "151659": {
135
+ "content": "<|fim_prefix|>",
136
+ "lstrip": false,
137
+ "normalized": false,
138
+ "rstrip": false,
139
+ "single_word": false,
140
+ "special": false
141
+ },
142
+ "151660": {
143
+ "content": "<|fim_middle|>",
144
+ "lstrip": false,
145
+ "normalized": false,
146
+ "rstrip": false,
147
+ "single_word": false,
148
+ "special": false
149
+ },
150
+ "151661": {
151
+ "content": "<|fim_suffix|>",
152
+ "lstrip": false,
153
+ "normalized": false,
154
+ "rstrip": false,
155
+ "single_word": false,
156
+ "special": false
157
+ },
158
+ "151662": {
159
+ "content": "<|fim_pad|>",
160
+ "lstrip": false,
161
+ "normalized": false,
162
+ "rstrip": false,
163
+ "single_word": false,
164
+ "special": false
165
+ },
166
+ "151663": {
167
+ "content": "<|repo_name|>",
168
+ "lstrip": false,
169
+ "normalized": false,
170
+ "rstrip": false,
171
+ "single_word": false,
172
+ "special": false
173
+ },
174
+ "151664": {
175
+ "content": "<|file_sep|>",
176
+ "lstrip": false,
177
+ "normalized": false,
178
+ "rstrip": false,
179
+ "single_word": false,
180
+ "special": false
181
+ },
182
+ "151665": {
183
+ "content": "<|0-0|>",
184
+ "lstrip": false,
185
+ "normalized": true,
186
+ "rstrip": false,
187
+ "single_word": false,
188
+ "special": false
189
+ },
190
+ "151666": {
191
+ "content": "<|0-1|>",
192
+ "lstrip": false,
193
+ "normalized": true,
194
+ "rstrip": false,
195
+ "single_word": false,
196
+ "special": false
197
+ },
198
+ "151667": {
199
+ "content": "<|0-2|>",
200
+ "lstrip": false,
201
+ "normalized": true,
202
+ "rstrip": false,
203
+ "single_word": false,
204
+ "special": false
205
+ },
206
+ "151668": {
207
+ "content": "<|0-3|>",
208
+ "lstrip": false,
209
+ "normalized": true,
210
+ "rstrip": false,
211
+ "single_word": false,
212
+ "special": false
213
+ },
214
+ "151669": {
215
+ "content": "<|0-4|>",
216
+ "lstrip": false,
217
+ "normalized": true,
218
+ "rstrip": false,
219
+ "single_word": false,
220
+ "special": false
221
+ },
222
+ "151670": {
223
+ "content": "<|1-0|>",
224
+ "lstrip": false,
225
+ "normalized": true,
226
+ "rstrip": false,
227
+ "single_word": false,
228
+ "special": false
229
+ },
230
+ "151671": {
231
+ "content": "<|1-1|>",
232
+ "lstrip": false,
233
+ "normalized": true,
234
+ "rstrip": false,
235
+ "single_word": false,
236
+ "special": false
237
+ },
238
+ "151672": {
239
+ "content": "<|1-2|>",
240
+ "lstrip": false,
241
+ "normalized": true,
242
+ "rstrip": false,
243
+ "single_word": false,
244
+ "special": false
245
+ },
246
+ "151673": {
247
+ "content": "<|1-3|>",
248
+ "lstrip": false,
249
+ "normalized": true,
250
+ "rstrip": false,
251
+ "single_word": false,
252
+ "special": false
253
+ },
254
+ "151674": {
255
+ "content": "<|1-4|>",
256
+ "lstrip": false,
257
+ "normalized": true,
258
+ "rstrip": false,
259
+ "single_word": false,
260
+ "special": false
261
+ },
262
+ "151675": {
263
+ "content": "<|2-0|>",
264
+ "lstrip": false,
265
+ "normalized": true,
266
+ "rstrip": false,
267
+ "single_word": false,
268
+ "special": false
269
+ },
270
+ "151676": {
271
+ "content": "<|2-1|>",
272
+ "lstrip": false,
273
+ "normalized": true,
274
+ "rstrip": false,
275
+ "single_word": false,
276
+ "special": false
277
+ },
278
+ "151677": {
279
+ "content": "<|2-2|>",
280
+ "lstrip": false,
281
+ "normalized": true,
282
+ "rstrip": false,
283
+ "single_word": false,
284
+ "special": false
285
+ },
286
+ "151678": {
287
+ "content": "<|2-3|>",
288
+ "lstrip": false,
289
+ "normalized": true,
290
+ "rstrip": false,
291
+ "single_word": false,
292
+ "special": false
293
+ },
294
+ "151679": {
295
+ "content": "<|2-4|>",
296
+ "lstrip": false,
297
+ "normalized": true,
298
+ "rstrip": false,
299
+ "single_word": false,
300
+ "special": false
301
+ },
302
+ "151680": {
303
+ "content": "<|3-0|>",
304
+ "lstrip": false,
305
+ "normalized": true,
306
+ "rstrip": false,
307
+ "single_word": false,
308
+ "special": false
309
+ },
310
+ "151681": {
311
+ "content": "<|3-1|>",
312
+ "lstrip": false,
313
+ "normalized": true,
314
+ "rstrip": false,
315
+ "single_word": false,
316
+ "special": false
317
+ },
318
+ "151682": {
319
+ "content": "<|3-2|>",
320
+ "lstrip": false,
321
+ "normalized": true,
322
+ "rstrip": false,
323
+ "single_word": false,
324
+ "special": false
325
+ },
326
+ "151683": {
327
+ "content": "<|3-3|>",
328
+ "lstrip": false,
329
+ "normalized": true,
330
+ "rstrip": false,
331
+ "single_word": false,
332
+ "special": false
333
+ },
334
+ "151684": {
335
+ "content": "<|3-4|>",
336
+ "lstrip": false,
337
+ "normalized": true,
338
+ "rstrip": false,
339
+ "single_word": false,
340
+ "special": false
341
+ },
342
+ "151685": {
343
+ "content": "<|4-0|>",
344
+ "lstrip": false,
345
+ "normalized": true,
346
+ "rstrip": false,
347
+ "single_word": false,
348
+ "special": false
349
+ },
350
+ "151686": {
351
+ "content": "<|4-1|>",
352
+ "lstrip": false,
353
+ "normalized": true,
354
+ "rstrip": false,
355
+ "single_word": false,
356
+ "special": false
357
+ },
358
+ "151687": {
359
+ "content": "<|4-2|>",
360
+ "lstrip": false,
361
+ "normalized": true,
362
+ "rstrip": false,
363
+ "single_word": false,
364
+ "special": false
365
+ },
366
+ "151688": {
367
+ "content": "<|4-3|>",
368
+ "lstrip": false,
369
+ "normalized": true,
370
+ "rstrip": false,
371
+ "single_word": false,
372
+ "special": false
373
+ },
374
+ "151689": {
375
+ "content": "<|4-4|>",
376
+ "lstrip": false,
377
+ "normalized": true,
378
+ "rstrip": false,
379
+ "single_word": false,
380
+ "special": false
381
+ },
382
+ "151690": {
383
+ "content": "<|up|>",
384
+ "lstrip": false,
385
+ "normalized": true,
386
+ "rstrip": false,
387
+ "single_word": false,
388
+ "special": false
389
+ },
390
+ "151691": {
391
+ "content": "<|down|>",
392
+ "lstrip": false,
393
+ "normalized": true,
394
+ "rstrip": false,
395
+ "single_word": false,
396
+ "special": false
397
+ },
398
+ "151692": {
399
+ "content": "<|left|>",
400
+ "lstrip": false,
401
+ "normalized": true,
402
+ "rstrip": false,
403
+ "single_word": false,
404
+ "special": false
405
+ },
406
+ "151693": {
407
+ "content": "<|right|>",
408
+ "lstrip": false,
409
+ "normalized": true,
410
+ "rstrip": false,
411
+ "single_word": false,
412
+ "special": false
413
+ },
414
+ "151694": {
415
+ "content": "<|blank|>",
416
+ "lstrip": false,
417
+ "normalized": true,
418
+ "rstrip": false,
419
+ "single_word": false,
420
+ "special": false
421
+ },
422
+ "151695": {
423
+ "content": "<|origin|>",
424
+ "lstrip": false,
425
+ "normalized": true,
426
+ "rstrip": false,
427
+ "single_word": false,
428
+ "special": false
429
+ },
430
+ "151696": {
431
+ "content": "<|target|>",
432
+ "lstrip": false,
433
+ "normalized": true,
434
+ "rstrip": false,
435
+ "single_word": false,
436
+ "special": false
437
+ },
438
+ "151697": {
439
+ "content": "<|no_wall|>",
440
+ "lstrip": false,
441
+ "normalized": true,
442
+ "rstrip": false,
443
+ "single_word": false,
444
+ "special": false
445
+ },
446
+ "151698": {
447
+ "content": "<|up_wall|>",
448
+ "lstrip": false,
449
+ "normalized": true,
450
+ "rstrip": false,
451
+ "single_word": false,
452
+ "special": false
453
+ },
454
+ "151699": {
455
+ "content": "<|down_wall|>",
456
+ "lstrip": false,
457
+ "normalized": true,
458
+ "rstrip": false,
459
+ "single_word": false,
460
+ "special": false
461
+ },
462
+ "151700": {
463
+ "content": "<|left_wall|>",
464
+ "lstrip": false,
465
+ "normalized": true,
466
+ "rstrip": false,
467
+ "single_word": false,
468
+ "special": false
469
+ },
470
+ "151701": {
471
+ "content": "<|right_wall|>",
472
+ "lstrip": false,
473
+ "normalized": true,
474
+ "rstrip": false,
475
+ "single_word": false,
476
+ "special": false
477
+ },
478
+ "151702": {
479
+ "content": "<|up_down_wall|>",
480
+ "lstrip": false,
481
+ "normalized": true,
482
+ "rstrip": false,
483
+ "single_word": false,
484
+ "special": false
485
+ },
486
+ "151703": {
487
+ "content": "<|up_left_wall|>",
488
+ "lstrip": false,
489
+ "normalized": true,
490
+ "rstrip": false,
491
+ "single_word": false,
492
+ "special": false
493
+ },
494
+ "151704": {
495
+ "content": "<|up_right_wall|>",
496
+ "lstrip": false,
497
+ "normalized": true,
498
+ "rstrip": false,
499
+ "single_word": false,
500
+ "special": false
501
+ },
502
+ "151705": {
503
+ "content": "<|down_left_wall|>",
504
+ "lstrip": false,
505
+ "normalized": true,
506
+ "rstrip": false,
507
+ "single_word": false,
508
+ "special": false
509
+ },
510
+ "151706": {
511
+ "content": "<|down_right_wall|>",
512
+ "lstrip": false,
513
+ "normalized": true,
514
+ "rstrip": false,
515
+ "single_word": false,
516
+ "special": false
517
+ },
518
+ "151707": {
519
+ "content": "<|left_right_wall|>",
520
+ "lstrip": false,
521
+ "normalized": true,
522
+ "rstrip": false,
523
+ "single_word": false,
524
+ "special": false
525
+ },
526
+ "151708": {
527
+ "content": "<|up_down_left_wall|>",
528
+ "lstrip": false,
529
+ "normalized": true,
530
+ "rstrip": false,
531
+ "single_word": false,
532
+ "special": false
533
+ },
534
+ "151709": {
535
+ "content": "<|up_down_right_wall|>",
536
+ "lstrip": false,
537
+ "normalized": true,
538
+ "rstrip": false,
539
+ "single_word": false,
540
+ "special": false
541
+ },
542
+ "151710": {
543
+ "content": "<|up_left_right_wall|>",
544
+ "lstrip": false,
545
+ "normalized": true,
546
+ "rstrip": false,
547
+ "single_word": false,
548
+ "special": false
549
+ },
550
+ "151711": {
551
+ "content": "<|down_left_right_wall|>",
552
+ "lstrip": false,
553
+ "normalized": true,
554
+ "rstrip": false,
555
+ "single_word": false,
556
+ "special": false
557
+ },
558
+ "151712": {
559
+ "content": "<|all_wall|>",
560
+ "lstrip": false,
561
+ "normalized": true,
562
+ "rstrip": false,
563
+ "single_word": false,
564
+ "special": false
565
+ }
566
+ },
567
+ "bos_token": "<|begin▁of▁sentence|>",
568
+ "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<|User|>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<|Assistant|><|tool▁calls▁begin|><|tool▁call▁begin|>' + tool['type'] + '<|tool▁sep|>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<|tool▁call▁end|>'}}{%- set ns.is_first = true -%}{%- else %}{{'\\n' + '<|tool▁call▁begin|>' + tool['type'] + '<|tool▁sep|>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<|tool▁call▁end|>'}}{{'<|tool▁calls▁end|><|end▁of▁sentence|>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<|tool▁outputs▁end|>' + message['content'] + '<|end▁of▁sentence|>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{{'<|Assistant|>' + content + '<|end▁of▁sentence|>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<|tool▁outputs▁begin|><|tool▁output▁begin|>' + message['content'] + '<|tool▁output▁end|>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\\n<|tool▁output▁begin|>' + message['content'] + '<|tool▁output▁end|>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<|tool▁outputs▁end|>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<|Assistant|><think>\\n'}}{% endif %}",
569
+ "clean_up_tokenization_spaces": false,
570
+ "eos_token": "<|end▁of▁sentence|>",
571
+ "extra_special_tokens": {},
572
+ "legacy": true,
573
+ "max_length": null,
574
+ "model_max_length": 131072,
575
+ "pad_to_multiple_of": null,
576
+ "pad_token": "<|vision_pad|>",
577
+ "pad_token_type_id": 0,
578
+ "padding_side": "left",
579
+ "sp_model_kwargs": {},
580
+ "split_special_tokens": false,
581
+ "tokenizer_class": "LlamaTokenizerFast",
582
+ "unk_token": null,
583
+ "use_default_system_prompt": false
584
+ }