onnx/tokenizer_config.json
20.4 KB · 942 lines · json Raw
1 {
2 "added_tokens_decoder": {
3 "0": {
4 "content": "<pad>",
5 "lstrip": false,
6 "normalized": false,
7 "rstrip": false,
8 "single_word": false,
9 "special": true
10 },
11 "1": {
12 "content": "</s>",
13 "lstrip": false,
14 "normalized": false,
15 "rstrip": false,
16 "single_word": false,
17 "special": true
18 },
19 "2": {
20 "content": "<unk>",
21 "lstrip": false,
22 "normalized": false,
23 "rstrip": false,
24 "single_word": false,
25 "special": true
26 },
27 "32000": {
28 "content": "<extra_id_99>",
29 "lstrip": false,
30 "normalized": false,
31 "rstrip": false,
32 "single_word": false,
33 "special": true
34 },
35 "32001": {
36 "content": "<extra_id_98>",
37 "lstrip": false,
38 "normalized": false,
39 "rstrip": false,
40 "single_word": false,
41 "special": true
42 },
43 "32002": {
44 "content": "<extra_id_97>",
45 "lstrip": false,
46 "normalized": false,
47 "rstrip": false,
48 "single_word": false,
49 "special": true
50 },
51 "32003": {
52 "content": "<extra_id_96>",
53 "lstrip": false,
54 "normalized": false,
55 "rstrip": false,
56 "single_word": false,
57 "special": true
58 },
59 "32004": {
60 "content": "<extra_id_95>",
61 "lstrip": false,
62 "normalized": false,
63 "rstrip": false,
64 "single_word": false,
65 "special": true
66 },
67 "32005": {
68 "content": "<extra_id_94>",
69 "lstrip": false,
70 "normalized": false,
71 "rstrip": false,
72 "single_word": false,
73 "special": true
74 },
75 "32006": {
76 "content": "<extra_id_93>",
77 "lstrip": false,
78 "normalized": false,
79 "rstrip": false,
80 "single_word": false,
81 "special": true
82 },
83 "32007": {
84 "content": "<extra_id_92>",
85 "lstrip": false,
86 "normalized": false,
87 "rstrip": false,
88 "single_word": false,
89 "special": true
90 },
91 "32008": {
92 "content": "<extra_id_91>",
93 "lstrip": false,
94 "normalized": false,
95 "rstrip": false,
96 "single_word": false,
97 "special": true
98 },
99 "32009": {
100 "content": "<extra_id_90>",
101 "lstrip": false,
102 "normalized": false,
103 "rstrip": false,
104 "single_word": false,
105 "special": true
106 },
107 "32010": {
108 "content": "<extra_id_89>",
109 "lstrip": false,
110 "normalized": false,
111 "rstrip": false,
112 "single_word": false,
113 "special": true
114 },
115 "32011": {
116 "content": "<extra_id_88>",
117 "lstrip": false,
118 "normalized": false,
119 "rstrip": false,
120 "single_word": false,
121 "special": true
122 },
123 "32012": {
124 "content": "<extra_id_87>",
125 "lstrip": false,
126 "normalized": false,
127 "rstrip": false,
128 "single_word": false,
129 "special": true
130 },
131 "32013": {
132 "content": "<extra_id_86>",
133 "lstrip": false,
134 "normalized": false,
135 "rstrip": false,
136 "single_word": false,
137 "special": true
138 },
139 "32014": {
140 "content": "<extra_id_85>",
141 "lstrip": false,
142 "normalized": false,
143 "rstrip": false,
144 "single_word": false,
145 "special": true
146 },
147 "32015": {
148 "content": "<extra_id_84>",
149 "lstrip": false,
150 "normalized": false,
151 "rstrip": false,
152 "single_word": false,
153 "special": true
154 },
155 "32016": {
156 "content": "<extra_id_83>",
157 "lstrip": false,
158 "normalized": false,
159 "rstrip": false,
160 "single_word": false,
161 "special": true
162 },
163 "32017": {
164 "content": "<extra_id_82>",
165 "lstrip": false,
166 "normalized": false,
167 "rstrip": false,
168 "single_word": false,
169 "special": true
170 },
171 "32018": {
172 "content": "<extra_id_81>",
173 "lstrip": false,
174 "normalized": false,
175 "rstrip": false,
176 "single_word": false,
177 "special": true
178 },
179 "32019": {
180 "content": "<extra_id_80>",
181 "lstrip": false,
182 "normalized": false,
183 "rstrip": false,
184 "single_word": false,
185 "special": true
186 },
187 "32020": {
188 "content": "<extra_id_79>",
189 "lstrip": false,
190 "normalized": false,
191 "rstrip": false,
192 "single_word": false,
193 "special": true
194 },
195 "32021": {
196 "content": "<extra_id_78>",
197 "lstrip": false,
198 "normalized": false,
199 "rstrip": false,
200 "single_word": false,
201 "special": true
202 },
203 "32022": {
204 "content": "<extra_id_77>",
205 "lstrip": false,
206 "normalized": false,
207 "rstrip": false,
208 "single_word": false,
209 "special": true
210 },
211 "32023": {
212 "content": "<extra_id_76>",
213 "lstrip": false,
214 "normalized": false,
215 "rstrip": false,
216 "single_word": false,
217 "special": true
218 },
219 "32024": {
220 "content": "<extra_id_75>",
221 "lstrip": false,
222 "normalized": false,
223 "rstrip": false,
224 "single_word": false,
225 "special": true
226 },
227 "32025": {
228 "content": "<extra_id_74>",
229 "lstrip": false,
230 "normalized": false,
231 "rstrip": false,
232 "single_word": false,
233 "special": true
234 },
235 "32026": {
236 "content": "<extra_id_73>",
237 "lstrip": false,
238 "normalized": false,
239 "rstrip": false,
240 "single_word": false,
241 "special": true
242 },
243 "32027": {
244 "content": "<extra_id_72>",
245 "lstrip": false,
246 "normalized": false,
247 "rstrip": false,
248 "single_word": false,
249 "special": true
250 },
251 "32028": {
252 "content": "<extra_id_71>",
253 "lstrip": false,
254 "normalized": false,
255 "rstrip": false,
256 "single_word": false,
257 "special": true
258 },
259 "32029": {
260 "content": "<extra_id_70>",
261 "lstrip": false,
262 "normalized": false,
263 "rstrip": false,
264 "single_word": false,
265 "special": true
266 },
267 "32030": {
268 "content": "<extra_id_69>",
269 "lstrip": false,
270 "normalized": false,
271 "rstrip": false,
272 "single_word": false,
273 "special": true
274 },
275 "32031": {
276 "content": "<extra_id_68>",
277 "lstrip": false,
278 "normalized": false,
279 "rstrip": false,
280 "single_word": false,
281 "special": true
282 },
283 "32032": {
284 "content": "<extra_id_67>",
285 "lstrip": false,
286 "normalized": false,
287 "rstrip": false,
288 "single_word": false,
289 "special": true
290 },
291 "32033": {
292 "content": "<extra_id_66>",
293 "lstrip": false,
294 "normalized": false,
295 "rstrip": false,
296 "single_word": false,
297 "special": true
298 },
299 "32034": {
300 "content": "<extra_id_65>",
301 "lstrip": false,
302 "normalized": false,
303 "rstrip": false,
304 "single_word": false,
305 "special": true
306 },
307 "32035": {
308 "content": "<extra_id_64>",
309 "lstrip": false,
310 "normalized": false,
311 "rstrip": false,
312 "single_word": false,
313 "special": true
314 },
315 "32036": {
316 "content": "<extra_id_63>",
317 "lstrip": false,
318 "normalized": false,
319 "rstrip": false,
320 "single_word": false,
321 "special": true
322 },
323 "32037": {
324 "content": "<extra_id_62>",
325 "lstrip": false,
326 "normalized": false,
327 "rstrip": false,
328 "single_word": false,
329 "special": true
330 },
331 "32038": {
332 "content": "<extra_id_61>",
333 "lstrip": false,
334 "normalized": false,
335 "rstrip": false,
336 "single_word": false,
337 "special": true
338 },
339 "32039": {
340 "content": "<extra_id_60>",
341 "lstrip": false,
342 "normalized": false,
343 "rstrip": false,
344 "single_word": false,
345 "special": true
346 },
347 "32040": {
348 "content": "<extra_id_59>",
349 "lstrip": false,
350 "normalized": false,
351 "rstrip": false,
352 "single_word": false,
353 "special": true
354 },
355 "32041": {
356 "content": "<extra_id_58>",
357 "lstrip": false,
358 "normalized": false,
359 "rstrip": false,
360 "single_word": false,
361 "special": true
362 },
363 "32042": {
364 "content": "<extra_id_57>",
365 "lstrip": false,
366 "normalized": false,
367 "rstrip": false,
368 "single_word": false,
369 "special": true
370 },
371 "32043": {
372 "content": "<extra_id_56>",
373 "lstrip": false,
374 "normalized": false,
375 "rstrip": false,
376 "single_word": false,
377 "special": true
378 },
379 "32044": {
380 "content": "<extra_id_55>",
381 "lstrip": false,
382 "normalized": false,
383 "rstrip": false,
384 "single_word": false,
385 "special": true
386 },
387 "32045": {
388 "content": "<extra_id_54>",
389 "lstrip": false,
390 "normalized": false,
391 "rstrip": false,
392 "single_word": false,
393 "special": true
394 },
395 "32046": {
396 "content": "<extra_id_53>",
397 "lstrip": false,
398 "normalized": false,
399 "rstrip": false,
400 "single_word": false,
401 "special": true
402 },
403 "32047": {
404 "content": "<extra_id_52>",
405 "lstrip": false,
406 "normalized": false,
407 "rstrip": false,
408 "single_word": false,
409 "special": true
410 },
411 "32048": {
412 "content": "<extra_id_51>",
413 "lstrip": false,
414 "normalized": false,
415 "rstrip": false,
416 "single_word": false,
417 "special": true
418 },
419 "32049": {
420 "content": "<extra_id_50>",
421 "lstrip": false,
422 "normalized": false,
423 "rstrip": false,
424 "single_word": false,
425 "special": true
426 },
427 "32050": {
428 "content": "<extra_id_49>",
429 "lstrip": false,
430 "normalized": false,
431 "rstrip": false,
432 "single_word": false,
433 "special": true
434 },
435 "32051": {
436 "content": "<extra_id_48>",
437 "lstrip": false,
438 "normalized": false,
439 "rstrip": false,
440 "single_word": false,
441 "special": true
442 },
443 "32052": {
444 "content": "<extra_id_47>",
445 "lstrip": false,
446 "normalized": false,
447 "rstrip": false,
448 "single_word": false,
449 "special": true
450 },
451 "32053": {
452 "content": "<extra_id_46>",
453 "lstrip": false,
454 "normalized": false,
455 "rstrip": false,
456 "single_word": false,
457 "special": true
458 },
459 "32054": {
460 "content": "<extra_id_45>",
461 "lstrip": false,
462 "normalized": false,
463 "rstrip": false,
464 "single_word": false,
465 "special": true
466 },
467 "32055": {
468 "content": "<extra_id_44>",
469 "lstrip": false,
470 "normalized": false,
471 "rstrip": false,
472 "single_word": false,
473 "special": true
474 },
475 "32056": {
476 "content": "<extra_id_43>",
477 "lstrip": false,
478 "normalized": false,
479 "rstrip": false,
480 "single_word": false,
481 "special": true
482 },
483 "32057": {
484 "content": "<extra_id_42>",
485 "lstrip": false,
486 "normalized": false,
487 "rstrip": false,
488 "single_word": false,
489 "special": true
490 },
491 "32058": {
492 "content": "<extra_id_41>",
493 "lstrip": false,
494 "normalized": false,
495 "rstrip": false,
496 "single_word": false,
497 "special": true
498 },
499 "32059": {
500 "content": "<extra_id_40>",
501 "lstrip": false,
502 "normalized": false,
503 "rstrip": false,
504 "single_word": false,
505 "special": true
506 },
507 "32060": {
508 "content": "<extra_id_39>",
509 "lstrip": false,
510 "normalized": false,
511 "rstrip": false,
512 "single_word": false,
513 "special": true
514 },
515 "32061": {
516 "content": "<extra_id_38>",
517 "lstrip": false,
518 "normalized": false,
519 "rstrip": false,
520 "single_word": false,
521 "special": true
522 },
523 "32062": {
524 "content": "<extra_id_37>",
525 "lstrip": false,
526 "normalized": false,
527 "rstrip": false,
528 "single_word": false,
529 "special": true
530 },
531 "32063": {
532 "content": "<extra_id_36>",
533 "lstrip": false,
534 "normalized": false,
535 "rstrip": false,
536 "single_word": false,
537 "special": true
538 },
539 "32064": {
540 "content": "<extra_id_35>",
541 "lstrip": false,
542 "normalized": false,
543 "rstrip": false,
544 "single_word": false,
545 "special": true
546 },
547 "32065": {
548 "content": "<extra_id_34>",
549 "lstrip": false,
550 "normalized": false,
551 "rstrip": false,
552 "single_word": false,
553 "special": true
554 },
555 "32066": {
556 "content": "<extra_id_33>",
557 "lstrip": false,
558 "normalized": false,
559 "rstrip": false,
560 "single_word": false,
561 "special": true
562 },
563 "32067": {
564 "content": "<extra_id_32>",
565 "lstrip": false,
566 "normalized": false,
567 "rstrip": false,
568 "single_word": false,
569 "special": true
570 },
571 "32068": {
572 "content": "<extra_id_31>",
573 "lstrip": false,
574 "normalized": false,
575 "rstrip": false,
576 "single_word": false,
577 "special": true
578 },
579 "32069": {
580 "content": "<extra_id_30>",
581 "lstrip": false,
582 "normalized": false,
583 "rstrip": false,
584 "single_word": false,
585 "special": true
586 },
587 "32070": {
588 "content": "<extra_id_29>",
589 "lstrip": false,
590 "normalized": false,
591 "rstrip": false,
592 "single_word": false,
593 "special": true
594 },
595 "32071": {
596 "content": "<extra_id_28>",
597 "lstrip": false,
598 "normalized": false,
599 "rstrip": false,
600 "single_word": false,
601 "special": true
602 },
603 "32072": {
604 "content": "<extra_id_27>",
605 "lstrip": false,
606 "normalized": false,
607 "rstrip": false,
608 "single_word": false,
609 "special": true
610 },
611 "32073": {
612 "content": "<extra_id_26>",
613 "lstrip": false,
614 "normalized": false,
615 "rstrip": false,
616 "single_word": false,
617 "special": true
618 },
619 "32074": {
620 "content": "<extra_id_25>",
621 "lstrip": false,
622 "normalized": false,
623 "rstrip": false,
624 "single_word": false,
625 "special": true
626 },
627 "32075": {
628 "content": "<extra_id_24>",
629 "lstrip": false,
630 "normalized": false,
631 "rstrip": false,
632 "single_word": false,
633 "special": true
634 },
635 "32076": {
636 "content": "<extra_id_23>",
637 "lstrip": false,
638 "normalized": false,
639 "rstrip": false,
640 "single_word": false,
641 "special": true
642 },
643 "32077": {
644 "content": "<extra_id_22>",
645 "lstrip": false,
646 "normalized": false,
647 "rstrip": false,
648 "single_word": false,
649 "special": true
650 },
651 "32078": {
652 "content": "<extra_id_21>",
653 "lstrip": false,
654 "normalized": false,
655 "rstrip": false,
656 "single_word": false,
657 "special": true
658 },
659 "32079": {
660 "content": "<extra_id_20>",
661 "lstrip": false,
662 "normalized": false,
663 "rstrip": false,
664 "single_word": false,
665 "special": true
666 },
667 "32080": {
668 "content": "<extra_id_19>",
669 "lstrip": false,
670 "normalized": false,
671 "rstrip": false,
672 "single_word": false,
673 "special": true
674 },
675 "32081": {
676 "content": "<extra_id_18>",
677 "lstrip": false,
678 "normalized": false,
679 "rstrip": false,
680 "single_word": false,
681 "special": true
682 },
683 "32082": {
684 "content": "<extra_id_17>",
685 "lstrip": false,
686 "normalized": false,
687 "rstrip": false,
688 "single_word": false,
689 "special": true
690 },
691 "32083": {
692 "content": "<extra_id_16>",
693 "lstrip": false,
694 "normalized": false,
695 "rstrip": false,
696 "single_word": false,
697 "special": true
698 },
699 "32084": {
700 "content": "<extra_id_15>",
701 "lstrip": false,
702 "normalized": false,
703 "rstrip": false,
704 "single_word": false,
705 "special": true
706 },
707 "32085": {
708 "content": "<extra_id_14>",
709 "lstrip": false,
710 "normalized": false,
711 "rstrip": false,
712 "single_word": false,
713 "special": true
714 },
715 "32086": {
716 "content": "<extra_id_13>",
717 "lstrip": false,
718 "normalized": false,
719 "rstrip": false,
720 "single_word": false,
721 "special": true
722 },
723 "32087": {
724 "content": "<extra_id_12>",
725 "lstrip": false,
726 "normalized": false,
727 "rstrip": false,
728 "single_word": false,
729 "special": true
730 },
731 "32088": {
732 "content": "<extra_id_11>",
733 "lstrip": false,
734 "normalized": false,
735 "rstrip": false,
736 "single_word": false,
737 "special": true
738 },
739 "32089": {
740 "content": "<extra_id_10>",
741 "lstrip": false,
742 "normalized": false,
743 "rstrip": false,
744 "single_word": false,
745 "special": true
746 },
747 "32090": {
748 "content": "<extra_id_9>",
749 "lstrip": false,
750 "normalized": false,
751 "rstrip": false,
752 "single_word": false,
753 "special": true
754 },
755 "32091": {
756 "content": "<extra_id_8>",
757 "lstrip": false,
758 "normalized": false,
759 "rstrip": false,
760 "single_word": false,
761 "special": true
762 },
763 "32092": {
764 "content": "<extra_id_7>",
765 "lstrip": false,
766 "normalized": false,
767 "rstrip": false,
768 "single_word": false,
769 "special": true
770 },
771 "32093": {
772 "content": "<extra_id_6>",
773 "lstrip": false,
774 "normalized": false,
775 "rstrip": false,
776 "single_word": false,
777 "special": true
778 },
779 "32094": {
780 "content": "<extra_id_5>",
781 "lstrip": false,
782 "normalized": false,
783 "rstrip": false,
784 "single_word": false,
785 "special": true
786 },
787 "32095": {
788 "content": "<extra_id_4>",
789 "lstrip": false,
790 "normalized": false,
791 "rstrip": false,
792 "single_word": false,
793 "special": true
794 },
795 "32096": {
796 "content": "<extra_id_3>",
797 "lstrip": false,
798 "normalized": false,
799 "rstrip": false,
800 "single_word": false,
801 "special": true
802 },
803 "32097": {
804 "content": "<extra_id_2>",
805 "lstrip": false,
806 "normalized": false,
807 "rstrip": false,
808 "single_word": false,
809 "special": true
810 },
811 "32098": {
812 "content": "<extra_id_1>",
813 "lstrip": false,
814 "normalized": false,
815 "rstrip": false,
816 "single_word": false,
817 "special": true
818 },
819 "32099": {
820 "content": "<extra_id_0>",
821 "lstrip": false,
822 "normalized": false,
823 "rstrip": false,
824 "single_word": false,
825 "special": true
826 }
827 },
828 "additional_special_tokens": [
829 "<extra_id_0>",
830 "<extra_id_1>",
831 "<extra_id_2>",
832 "<extra_id_3>",
833 "<extra_id_4>",
834 "<extra_id_5>",
835 "<extra_id_6>",
836 "<extra_id_7>",
837 "<extra_id_8>",
838 "<extra_id_9>",
839 "<extra_id_10>",
840 "<extra_id_11>",
841 "<extra_id_12>",
842 "<extra_id_13>",
843 "<extra_id_14>",
844 "<extra_id_15>",
845 "<extra_id_16>",
846 "<extra_id_17>",
847 "<extra_id_18>",
848 "<extra_id_19>",
849 "<extra_id_20>",
850 "<extra_id_21>",
851 "<extra_id_22>",
852 "<extra_id_23>",
853 "<extra_id_24>",
854 "<extra_id_25>",
855 "<extra_id_26>",
856 "<extra_id_27>",
857 "<extra_id_28>",
858 "<extra_id_29>",
859 "<extra_id_30>",
860 "<extra_id_31>",
861 "<extra_id_32>",
862 "<extra_id_33>",
863 "<extra_id_34>",
864 "<extra_id_35>",
865 "<extra_id_36>",
866 "<extra_id_37>",
867 "<extra_id_38>",
868 "<extra_id_39>",
869 "<extra_id_40>",
870 "<extra_id_41>",
871 "<extra_id_42>",
872 "<extra_id_43>",
873 "<extra_id_44>",
874 "<extra_id_45>",
875 "<extra_id_46>",
876 "<extra_id_47>",
877 "<extra_id_48>",
878 "<extra_id_49>",
879 "<extra_id_50>",
880 "<extra_id_51>",
881 "<extra_id_52>",
882 "<extra_id_53>",
883 "<extra_id_54>",
884 "<extra_id_55>",
885 "<extra_id_56>",
886 "<extra_id_57>",
887 "<extra_id_58>",
888 "<extra_id_59>",
889 "<extra_id_60>",
890 "<extra_id_61>",
891 "<extra_id_62>",
892 "<extra_id_63>",
893 "<extra_id_64>",
894 "<extra_id_65>",
895 "<extra_id_66>",
896 "<extra_id_67>",
897 "<extra_id_68>",
898 "<extra_id_69>",
899 "<extra_id_70>",
900 "<extra_id_71>",
901 "<extra_id_72>",
902 "<extra_id_73>",
903 "<extra_id_74>",
904 "<extra_id_75>",
905 "<extra_id_76>",
906 "<extra_id_77>",
907 "<extra_id_78>",
908 "<extra_id_79>",
909 "<extra_id_80>",
910 "<extra_id_81>",
911 "<extra_id_82>",
912 "<extra_id_83>",
913 "<extra_id_84>",
914 "<extra_id_85>",
915 "<extra_id_86>",
916 "<extra_id_87>",
917 "<extra_id_88>",
918 "<extra_id_89>",
919 "<extra_id_90>",
920 "<extra_id_91>",
921 "<extra_id_92>",
922 "<extra_id_93>",
923 "<extra_id_94>",
924 "<extra_id_95>",
925 "<extra_id_96>",
926 "<extra_id_97>",
927 "<extra_id_98>",
928 "<extra_id_99>"
929 ],
930 "clean_up_tokenization_spaces": true,
931 "eos_token": "</s>",
932 "extra_ids": 100,
933 "max_length": 256,
934 "model_max_length": 512,
935 "pad_token": "<pad>",
936 "stride": 0,
937 "tokenizer_class": "T5Tokenizer",
938 "truncation_side": "right",
939 "truncation_strategy": "longest_first",
940 "unk_token": "<unk>"
941 }
942