tokenizer_config.json
12.2 KB · 549 lines · json Raw
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 "151665": {
182 "content": "<tool_response>",
183 "lstrip": false,
184 "normalized": false,
185 "rstrip": false,
186 "single_word": false,
187 "special": false
188 },
189 "151666": {
190 "content": "</tool_response>",
191 "lstrip": false,
192 "normalized": false,
193 "rstrip": false,
194 "single_word": false,
195 "special": false
196 },
197 "151667": {
198 "content": "<think>",
199 "lstrip": false,
200 "normalized": false,
201 "rstrip": false,
202 "single_word": false,
203 "special": false
204 },
205 "151668": {
206 "content": "</think>",
207 "lstrip": false,
208 "normalized": false,
209 "rstrip": false,
210 "single_word": false,
211 "special": false
212 },
213 "151669": {
214 "content": "<|audio_start|>",
215 "lstrip": false,
216 "normalized": false,
217 "rstrip": false,
218 "single_word": false,
219 "special": true
220 },
221 "151670": {
222 "content": "<|audio_end|>",
223 "lstrip": false,
224 "normalized": false,
225 "rstrip": false,
226 "single_word": false,
227 "special": true
228 },
229 "151671": {
230 "content": "<tts_pad>",
231 "lstrip": false,
232 "normalized": false,
233 "rstrip": false,
234 "single_word": false,
235 "special": true
236 },
237 "151672": {
238 "content": "<tts_text_bos>",
239 "lstrip": false,
240 "normalized": false,
241 "rstrip": false,
242 "single_word": false,
243 "special": true
244 },
245 "151673": {
246 "content": "<tts_text_eod>",
247 "lstrip": false,
248 "normalized": false,
249 "rstrip": false,
250 "single_word": false,
251 "special": true
252 },
253 "151674": {
254 "content": "<tts_text_bos_single>",
255 "lstrip": false,
256 "normalized": false,
257 "rstrip": false,
258 "single_word": false,
259 "special": true
260 },
261 "151675": {
262 "content": "<non_speech>",
263 "lstrip": false,
264 "normalized": false,
265 "rstrip": false,
266 "single_word": false,
267 "special": false
268 },
269 "151676": {
270 "content": "<|audio_pad|>",
271 "lstrip": false,
272 "normalized": false,
273 "rstrip": false,
274 "single_word": false,
275 "special": true
276 },
277 "151677": {
278 "content": "<blank1>",
279 "lstrip": false,
280 "normalized": false,
281 "rstrip": false,
282 "single_word": false,
283 "special": true
284 },
285 "151678": {
286 "content": "<blank2>",
287 "lstrip": false,
288 "normalized": false,
289 "rstrip": false,
290 "single_word": false,
291 "special": true
292 },
293 "151679": {
294 "content": "<blank3>",
295 "lstrip": false,
296 "normalized": false,
297 "rstrip": false,
298 "single_word": false,
299 "special": true
300 },
301 "151680": {
302 "content": "<blank4>",
303 "lstrip": false,
304 "normalized": false,
305 "rstrip": false,
306 "single_word": false,
307 "special": true
308 },
309 "151681": {
310 "content": "<blank5>",
311 "lstrip": false,
312 "normalized": false,
313 "rstrip": false,
314 "single_word": false,
315 "special": true
316 },
317 "151682": {
318 "content": "<blank6>",
319 "lstrip": false,
320 "normalized": false,
321 "rstrip": false,
322 "single_word": false,
323 "special": true
324 },
325 "151683": {
326 "content": "<blank7>",
327 "lstrip": false,
328 "normalized": false,
329 "rstrip": false,
330 "single_word": false,
331 "special": true
332 },
333 "151684": {
334 "content": "<blank8>",
335 "lstrip": false,
336 "normalized": false,
337 "rstrip": false,
338 "single_word": false,
339 "special": true
340 },
341 "151685": {
342 "content": "<blank9>",
343 "lstrip": false,
344 "normalized": false,
345 "rstrip": false,
346 "single_word": false,
347 "special": true
348 },
349 "151686": {
350 "content": "<blank10>",
351 "lstrip": false,
352 "normalized": false,
353 "rstrip": false,
354 "single_word": false,
355 "special": true
356 },
357 "151687": {
358 "content": "<blank11>",
359 "lstrip": false,
360 "normalized": false,
361 "rstrip": false,
362 "single_word": false,
363 "special": true
364 },
365 "151688": {
366 "content": "<blank12>",
367 "lstrip": false,
368 "normalized": false,
369 "rstrip": false,
370 "single_word": false,
371 "special": true
372 },
373 "151689": {
374 "content": "<blank13>",
375 "lstrip": false,
376 "normalized": false,
377 "rstrip": false,
378 "single_word": false,
379 "special": true
380 },
381 "151690": {
382 "content": "<blank14>",
383 "lstrip": false,
384 "normalized": false,
385 "rstrip": false,
386 "single_word": false,
387 "special": true
388 },
389 "151691": {
390 "content": "<blank15>",
391 "lstrip": false,
392 "normalized": false,
393 "rstrip": false,
394 "single_word": false,
395 "special": true
396 },
397 "151692": {
398 "content": "<blank16>",
399 "lstrip": false,
400 "normalized": false,
401 "rstrip": false,
402 "single_word": false,
403 "special": true
404 },
405 "151693": {
406 "content": "<blank17>",
407 "lstrip": false,
408 "normalized": false,
409 "rstrip": false,
410 "single_word": false,
411 "special": true
412 },
413 "151694": {
414 "content": "<blank18>",
415 "lstrip": false,
416 "normalized": false,
417 "rstrip": false,
418 "single_word": false,
419 "special": true
420 },
421 "151695": {
422 "content": "<blank19>",
423 "lstrip": false,
424 "normalized": false,
425 "rstrip": false,
426 "single_word": false,
427 "special": true
428 },
429 "151696": {
430 "content": "<blank20>",
431 "lstrip": false,
432 "normalized": false,
433 "rstrip": false,
434 "single_word": false,
435 "special": true
436 },
437 "151697": {
438 "content": "<blank21>",
439 "lstrip": false,
440 "normalized": false,
441 "rstrip": false,
442 "single_word": false,
443 "special": true
444 },
445 "151698": {
446 "content": "<blank22>",
447 "lstrip": false,
448 "normalized": false,
449 "rstrip": false,
450 "single_word": false,
451 "special": true
452 },
453 "151699": {
454 "content": "<blank23>",
455 "lstrip": false,
456 "normalized": false,
457 "rstrip": false,
458 "single_word": false,
459 "special": true
460 },
461 "151700": {
462 "content": "<blank24>",
463 "lstrip": false,
464 "normalized": false,
465 "rstrip": false,
466 "single_word": false,
467 "special": true
468 },
469 "151701": {
470 "content": "<blank25>",
471 "lstrip": false,
472 "normalized": false,
473 "rstrip": false,
474 "single_word": false,
475 "special": true
476 },
477 "151702": {
478 "content": "<blank26>",
479 "lstrip": false,
480 "normalized": false,
481 "rstrip": false,
482 "single_word": false,
483 "special": true
484 },
485 "151703": {
486 "content": "<blank27>",
487 "lstrip": false,
488 "normalized": false,
489 "rstrip": false,
490 "single_word": false,
491 "special": true
492 },
493 "151704": {
494 "content": "<asr_text>",
495 "lstrip": false,
496 "normalized": false,
497 "rstrip": false,
498 "single_word": false,
499 "special": false
500 }
501 },
502 "additional_special_tokens": [
503 "<|im_start|>",
504 "<|im_end|>",
505 "<|object_ref_start|>",
506 "<|object_ref_end|>",
507 "<|box_start|>",
508 "<|box_end|>",
509 "<|quad_start|>",
510 "<|quad_end|>",
511 "<|vision_start|>",
512 "<|vision_end|>",
513 "<|vision_pad|>",
514 "<|image_pad|>",
515 "<|video_pad|>",
516 "<|audio_start|>",
517 "<|audio_end|>",
518 "<tts_pad>",
519 "<tts_text_bos>",
520 "<tts_text_bos_single>",
521 "<|audio_pad|>"
522 ],
523 "audio_bos_token": "<|audio_start|>",
524 "audio_eos_token": "<|audio_end|>",
525 "audio_token": "<|audio_pad|>",
526 "bos_token": null,
527 "clean_up_tokenization_spaces": false,
528 "eos_token": "<|im_end|>",
529 "errors": "replace",
530 "extra_special_tokens": {
531 "audio_bos_token": "<|audio_start|>",
532 "audio_eos_token": "<|audio_end|>",
533 "audio_token": "<|audio_pad|>",
534 "image_token": "<|image_pad|>",
535 "video_token": "<|video_pad|>",
536 "vision_bos_token": "<|vision_start|>",
537 "vision_eos_token": "<|vision_end|>"
538 },
539 "image_token": "<|image_pad|>",
540 "model_max_length": 131072,
541 "pad_token": "<|endoftext|>",
542 "processor_class": "Qwen3ASRProcessor",
543 "split_special_tokens": false,
544 "tokenizer_class": "Qwen2Tokenizer",
545 "unk_token": null,
546 "video_token": "<|video_pad|>",
547 "vision_bos_token": "<|vision_start|>",
548 "vision_eos_token": "<|vision_end|>"
549 }