Upload tokenizer
Browse files- tokenizer.json +1081 -1034
- tokenizer_config.json +2 -10
tokenizer.json
CHANGED
@@ -14,7 +14,7 @@
|
|
14 |
},
|
15 |
{
|
16 |
"id": 1,
|
17 |
-
"content": "[
|
18 |
"single_word": false,
|
19 |
"lstrip": false,
|
20 |
"rstrip": false,
|
@@ -23,16 +23,7 @@
|
|
23 |
},
|
24 |
{
|
25 |
"id": 2,
|
26 |
-
"content": "[
|
27 |
-
"single_word": false,
|
28 |
-
"lstrip": false,
|
29 |
-
"rstrip": false,
|
30 |
-
"normalized": false,
|
31 |
-
"special": true
|
32 |
-
},
|
33 |
-
{
|
34 |
-
"id": 3,
|
35 |
-
"content": "[PAD]",
|
36 |
"single_word": false,
|
37 |
"lstrip": false,
|
38 |
"rstrip": false,
|
@@ -70,7 +61,63 @@
|
|
70 |
}
|
71 |
]
|
72 |
},
|
73 |
-
"post_processor":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
74 |
"decoder": null,
|
75 |
"model": {
|
76 |
"type": "WordPiece",
|
@@ -79,1029 +126,1029 @@
|
|
79 |
"max_input_chars_per_word": 100,
|
80 |
"vocab": {
|
81 |
"[UNK]": 0,
|
82 |
-
"[
|
83 |
-
"[
|
84 |
-
"
|
85 |
-
"
|
86 |
-
"
|
87 |
-
"
|
88 |
-
"
|
89 |
-
"
|
90 |
-
"
|
91 |
-
"
|
92 |
-
"
|
93 |
-
"
|
94 |
-
"
|
95 |
-
"
|
96 |
-
"
|
97 |
-
"
|
98 |
-
"
|
99 |
-
"
|
100 |
-
"
|
101 |
-
"
|
102 |
-
"
|
103 |
-
"
|
104 |
-
"
|
105 |
-
"
|
106 |
-
"
|
107 |
-
"
|
108 |
-
"
|
109 |
-
"
|
110 |
-
"
|
111 |
-
"
|
112 |
-
"
|
113 |
-
"
|
114 |
-
"
|
115 |
-
"
|
116 |
-
"
|
117 |
-
"
|
118 |
-
"
|
119 |
-
"
|
120 |
-
"
|
121 |
-
"
|
122 |
-
"
|
123 |
-
"
|
124 |
-
"
|
125 |
-
"
|
126 |
-
"
|
127 |
-
"
|
128 |
-
"
|
129 |
-
"
|
130 |
-
"
|
131 |
-
"
|
132 |
-
"
|
133 |
-
"
|
134 |
-
"
|
135 |
-
"
|
136 |
-
"
|
137 |
-
"
|
138 |
-
"
|
139 |
-
"
|
140 |
-
"
|
141 |
-
"
|
142 |
-
"
|
143 |
-
"
|
144 |
-
"
|
145 |
-
"
|
146 |
-
"
|
147 |
-
"
|
148 |
-
"
|
149 |
-
"
|
150 |
-
"
|
151 |
-
"
|
152 |
-
"##
|
153 |
-
"##
|
154 |
-
"##
|
155 |
-
"##
|
156 |
-
"##
|
157 |
-
"##
|
158 |
-
"##
|
159 |
-
"##
|
160 |
-
"##
|
161 |
-
"##
|
162 |
-
"##
|
163 |
-
"##
|
164 |
-
"##
|
165 |
-
"##
|
166 |
-
"##
|
167 |
-
"##
|
168 |
-
"##
|
169 |
-
"##
|
170 |
-
"##
|
171 |
-
"##
|
172 |
-
"##
|
173 |
-
"##
|
174 |
-
"##
|
175 |
"##j": 94,
|
176 |
-
"##
|
177 |
-
"##
|
178 |
-
"
|
179 |
-
"
|
180 |
-
"##
|
181 |
-
"
|
182 |
-
"
|
183 |
-
"
|
184 |
-
"
|
185 |
-
"
|
186 |
-
"##
|
187 |
-
"
|
188 |
-
"
|
189 |
-
"
|
190 |
-
"
|
191 |
-
"
|
192 |
-
"##
|
193 |
-
"
|
194 |
-
"
|
195 |
-
"##
|
196 |
-
"##
|
197 |
-
"##
|
198 |
-
"
|
199 |
-
"
|
200 |
-
"##
|
201 |
-
"
|
202 |
-
"
|
203 |
-
"
|
204 |
-
"##
|
205 |
-
"##
|
206 |
-
"
|
207 |
-
"
|
208 |
-
"
|
209 |
-
"##
|
210 |
-
"##
|
211 |
-
"##
|
212 |
-
"
|
213 |
-
"
|
214 |
-
"##
|
215 |
-
"##
|
216 |
-
"##
|
217 |
-
"##
|
218 |
-
"##
|
219 |
-
"
|
220 |
-
"
|
221 |
-
"
|
222 |
-
"
|
223 |
-
"##
|
224 |
-
"##
|
225 |
-
"
|
226 |
-
"
|
227 |
-
"
|
228 |
-
"
|
229 |
-
"
|
230 |
-
"
|
231 |
-
"
|
232 |
-
"
|
233 |
-
"##
|
234 |
-
"
|
235 |
-
"
|
236 |
-
"
|
237 |
-
"
|
238 |
-
"
|
239 |
-
"
|
240 |
-
"
|
241 |
-
"
|
242 |
-
"
|
243 |
-
"
|
244 |
-
"
|
245 |
-
"
|
246 |
-
"##
|
247 |
-
"##
|
248 |
-
"##
|
249 |
-
"##
|
250 |
-
"
|
251 |
-
"
|
252 |
-
"
|
253 |
-
"
|
254 |
-
"
|
255 |
-
"
|
256 |
-
"
|
257 |
-
"
|
258 |
-
"
|
259 |
-
"
|
260 |
-
"##
|
261 |
-
"##
|
262 |
-
"
|
263 |
-
"
|
264 |
-
"##
|
265 |
-
"
|
266 |
-
"
|
267 |
-
"##
|
268 |
-
"
|
269 |
-
"
|
270 |
-
"
|
271 |
-
"
|
272 |
-
"
|
273 |
-
"
|
274 |
-
"##
|
275 |
-
"
|
276 |
-
"
|
277 |
-
"
|
278 |
-
"##
|
279 |
-
"
|
280 |
-
"
|
281 |
-
"##
|
282 |
-
"
|
283 |
-
"
|
284 |
-
"
|
285 |
-
"
|
286 |
-
"
|
287 |
-
"
|
288 |
-
"
|
289 |
-
"##
|
290 |
-
"
|
291 |
-
"
|
292 |
-
"
|
293 |
-
"
|
294 |
-
"
|
295 |
-
"
|
296 |
-
"
|
297 |
-
"
|
298 |
-
"
|
299 |
-
"
|
300 |
-
"
|
301 |
-
"
|
302 |
-
"
|
303 |
-
"##
|
304 |
-
"##
|
305 |
-
"##
|
306 |
-
"##
|
307 |
-
"
|
308 |
-
"
|
309 |
-
"
|
310 |
-
"
|
311 |
-
"
|
312 |
-
"
|
313 |
-
"
|
314 |
-
"
|
315 |
-
"
|
316 |
-
"
|
317 |
-
"
|
318 |
-
"
|
319 |
-
"
|
320 |
-
"
|
321 |
-
"
|
322 |
-
"
|
323 |
-
"
|
324 |
-
"
|
325 |
-
"##
|
326 |
-
"
|
327 |
-
"
|
328 |
-
"
|
329 |
-
"
|
330 |
-
"
|
331 |
-
"
|
332 |
-
"
|
333 |
-
"
|
334 |
-
"
|
335 |
-
"
|
336 |
-
"
|
337 |
-
"##
|
338 |
-
"##
|
339 |
-
"
|
340 |
-
"
|
341 |
-
"
|
342 |
-
"
|
343 |
-
"
|
344 |
-
"
|
345 |
-
"
|
346 |
-
"##
|
347 |
-
"##
|
348 |
-
"##
|
349 |
-
"
|
350 |
-
"
|
351 |
-
"
|
352 |
-
"
|
353 |
-
"
|
354 |
-
"
|
355 |
-
"
|
356 |
-
"
|
357 |
-
"
|
358 |
-
"
|
359 |
-
"
|
360 |
-
"
|
361 |
-
"##
|
362 |
-
"
|
363 |
-
"
|
364 |
-
"
|
365 |
-
"
|
366 |
-
"
|
367 |
-
"
|
368 |
-
"
|
369 |
-
"
|
370 |
-
"
|
371 |
-
"
|
372 |
-
"##
|
373 |
-
"
|
374 |
-
"
|
375 |
-
"
|
376 |
-
"
|
377 |
-
"
|
378 |
-
"
|
379 |
-
"
|
380 |
-
"
|
381 |
-
"
|
382 |
-
"
|
383 |
-
"
|
384 |
-
"
|
385 |
-
"
|
386 |
-
"
|
387 |
-
"
|
388 |
-
"
|
389 |
-
"
|
390 |
-
"
|
391 |
-
"
|
392 |
-
"
|
393 |
-
"
|
394 |
-
"
|
395 |
-
"
|
396 |
-
"
|
397 |
-
"
|
398 |
-
"
|
399 |
-
"
|
400 |
-
"
|
401 |
-
"
|
402 |
-
"
|
403 |
-
"
|
404 |
-
"
|
405 |
-
"##
|
406 |
-
"##
|
407 |
-
"
|
408 |
-
"
|
409 |
-
"
|
410 |
-
"
|
411 |
-
"
|
412 |
-
"
|
413 |
-
"
|
414 |
-
"
|
415 |
-
"
|
416 |
-
"
|
417 |
-
"
|
418 |
-
"
|
419 |
-
"
|
420 |
-
"##
|
421 |
-
"
|
422 |
-
"
|
423 |
-
"
|
424 |
-
"
|
425 |
-
"
|
426 |
-
"
|
427 |
-
"
|
428 |
-
"
|
429 |
-
"
|
430 |
-
"
|
431 |
-
"
|
432 |
-
"
|
433 |
-
"
|
434 |
-
"
|
435 |
-
"
|
436 |
-
"
|
437 |
-
"
|
438 |
-
"
|
439 |
-
"##
|
440 |
-
"
|
441 |
-
"
|
442 |
-
"
|
443 |
-
"
|
444 |
-
"
|
445 |
-
"
|
446 |
-
"##
|
447 |
-
"
|
448 |
-
"
|
449 |
-
"
|
450 |
-
"
|
451 |
-
"
|
452 |
-
"
|
453 |
-
"
|
454 |
-
"
|
455 |
-
"
|
456 |
-
"
|
457 |
-
"
|
458 |
-
"
|
459 |
-
"
|
460 |
-
"
|
461 |
-
"
|
462 |
-
"
|
463 |
-
"
|
464 |
-
"
|
465 |
-
"
|
466 |
-
"
|
467 |
-
"
|
468 |
-
"##
|
469 |
-
"
|
470 |
-
"
|
471 |
-
"
|
472 |
-
"
|
473 |
-
"
|
474 |
-
"
|
475 |
-
"
|
476 |
-
"
|
477 |
-
"##
|
478 |
-
"
|
479 |
-
"
|
480 |
-
"
|
481 |
-
"
|
482 |
-
"
|
483 |
-
"
|
484 |
-
"
|
485 |
-
"
|
486 |
-
"
|
487 |
-
"##
|
488 |
-
"##
|
489 |
-
"##
|
490 |
-
"##
|
491 |
-
"
|
492 |
-
"
|
493 |
-
"
|
494 |
-
"
|
495 |
-
"
|
496 |
-
"
|
497 |
-
"
|
498 |
-
"
|
499 |
-
"
|
500 |
-
"
|
501 |
-
"
|
502 |
-
"
|
503 |
-
"
|
504 |
-
"
|
505 |
-
"
|
506 |
-
"
|
507 |
-
"
|
508 |
-
"
|
509 |
-
"
|
510 |
-
"
|
511 |
-
"
|
512 |
-
"
|
513 |
-
"
|
514 |
-
"##
|
515 |
-
"
|
516 |
-
"
|
517 |
-
"##
|
518 |
-
"##
|
519 |
-
"##
|
520 |
-
"##
|
521 |
-
"
|
522 |
-
"
|
523 |
-
"
|
524 |
-
"
|
525 |
-
"
|
526 |
-
"
|
527 |
-
"
|
528 |
-
"
|
529 |
-
"
|
530 |
-
"
|
531 |
-
"
|
532 |
-
"##
|
533 |
-
"##
|
534 |
-
"
|
535 |
-
"
|
536 |
-
"
|
537 |
-
"
|
538 |
-
"
|
539 |
-
"
|
540 |
-
"
|
541 |
-
"
|
542 |
-
"
|
543 |
-
"
|
544 |
-
"
|
545 |
-
"
|
546 |
-
"
|
547 |
-
"
|
548 |
-
"##
|
549 |
-
"##
|
550 |
-
"##
|
551 |
-
"
|
552 |
-
"
|
553 |
-
"
|
554 |
-
"
|
555 |
-
"
|
556 |
-
"
|
557 |
-
"
|
558 |
-
"
|
559 |
-
"
|
560 |
-
"
|
561 |
-
"
|
562 |
-
"
|
563 |
-
"
|
564 |
-
"
|
565 |
-
"
|
566 |
-
"
|
567 |
-
"
|
568 |
-
"
|
569 |
-
"
|
570 |
-
"
|
571 |
-
"
|
572 |
-
"##
|
573 |
-
"
|
574 |
-
"
|
575 |
-
"
|
576 |
-
"
|
577 |
-
"
|
578 |
-
"
|
579 |
-
"
|
580 |
-
"
|
581 |
-
"
|
582 |
-
"
|
583 |
-
"
|
584 |
-
"
|
585 |
-
"##
|
586 |
-
"
|
587 |
-
"
|
588 |
-
"
|
589 |
-
"
|
590 |
-
"
|
591 |
-
"
|
592 |
-
"
|
593 |
-
"
|
594 |
-
"
|
595 |
-
"
|
596 |
-
"
|
597 |
-
"
|
598 |
-
"
|
599 |
-
"
|
600 |
-
"
|
601 |
-
"
|
602 |
-
"
|
603 |
-
"
|
604 |
-
"
|
605 |
-
"
|
606 |
-
"
|
607 |
-
"
|
608 |
-
"
|
609 |
-
"
|
610 |
-
"
|
611 |
-
"
|
612 |
-
"
|
613 |
-
"
|
614 |
-
"
|
615 |
-
"
|
616 |
-
"##
|
617 |
-
"
|
618 |
-
"
|
619 |
-
"
|
620 |
-
"
|
621 |
-
"
|
622 |
-
"
|
623 |
-
"
|
624 |
-
"
|
625 |
-
"
|
626 |
-
"
|
627 |
-
"
|
628 |
-
"
|
629 |
-
"
|
630 |
-
"
|
631 |
-
"
|
632 |
-
"
|
633 |
-
"
|
634 |
-
"
|
635 |
-
"
|
636 |
-
"
|
637 |
-
"
|
638 |
-
"
|
639 |
-
"
|
640 |
-
"
|
641 |
-
"
|
642 |
-
"
|
643 |
-
"
|
644 |
-
"
|
645 |
-
"
|
646 |
-
"
|
647 |
-
"
|
648 |
-
"
|
649 |
-
"
|
650 |
-
"
|
651 |
-
"
|
652 |
-
"
|
653 |
-
"##
|
654 |
-
"##
|
655 |
-
"
|
656 |
-
"
|
657 |
-
"
|
658 |
-
"
|
659 |
-
"##
|
660 |
-
"##
|
661 |
-
"##
|
662 |
-
"
|
663 |
-
"
|
664 |
-
"
|
665 |
-
"
|
666 |
-
"
|
667 |
-
"
|
668 |
-
"
|
669 |
-
"##
|
670 |
-
"
|
671 |
-
"
|
672 |
-
"
|
673 |
-
"##
|
674 |
-
"##
|
675 |
-
"
|
676 |
-
"
|
677 |
-
"
|
678 |
-
"
|
679 |
-
"
|
680 |
-
"
|
681 |
-
"
|
682 |
-
"
|
683 |
-
"
|
684 |
-
"
|
685 |
-
"
|
686 |
-
"
|
687 |
-
"
|
688 |
-
"
|
689 |
-
"
|
690 |
-
"
|
691 |
-
"
|
692 |
-
"##
|
693 |
-
"##
|
694 |
-
"
|
695 |
-
"
|
696 |
-
"##
|
697 |
-
"##
|
698 |
-
"
|
699 |
-
"
|
700 |
-
"
|
701 |
-
"
|
702 |
-
"
|
703 |
-
"
|
704 |
-
"
|
705 |
-
"
|
706 |
-
"
|
707 |
-
"
|
708 |
-
"
|
709 |
-
"
|
710 |
-
"
|
711 |
-
"
|
712 |
-
"
|
713 |
-
"
|
714 |
-
"
|
715 |
-
"
|
716 |
-
"
|
717 |
-
"
|
718 |
-
"
|
719 |
-
"##
|
720 |
-
"##
|
721 |
-
"
|
722 |
-
"
|
723 |
-
"
|
724 |
-
"##
|
725 |
-
"
|
726 |
-
"
|
727 |
-
"
|
728 |
-
"
|
729 |
-
"
|
730 |
-
"
|
731 |
-
"
|
732 |
-
"
|
733 |
-
"
|
734 |
-
"
|
735 |
-
"
|
736 |
-
"
|
737 |
-
"
|
738 |
-
"
|
739 |
-
"
|
740 |
-
"
|
741 |
-
"
|
742 |
-
"##
|
743 |
-
"
|
744 |
-
"
|
745 |
-
"
|
746 |
-
"
|
747 |
-
"
|
748 |
-
"
|
749 |
-
"
|
750 |
-
"
|
751 |
-
"##
|
752 |
-
"
|
753 |
-
"
|
754 |
-
"
|
755 |
-
"
|
756 |
-
"
|
757 |
-
"
|
758 |
-
"##
|
759 |
-
"
|
760 |
-
"
|
761 |
-
"
|
762 |
-
"
|
763 |
-
"
|
764 |
-
"
|
765 |
-
"
|
766 |
-
"
|
767 |
-
"
|
768 |
-
"
|
769 |
-
"
|
770 |
-
"##
|
771 |
-
"##
|
772 |
-
"
|
773 |
-
"
|
774 |
-
"
|
775 |
-
"
|
776 |
-
"##
|
777 |
-
"
|
778 |
-
"
|
779 |
-
"
|
780 |
-
"
|
781 |
-
"##
|
782 |
-
"##
|
783 |
-
"
|
784 |
-
"
|
785 |
-
"
|
786 |
-
"
|
787 |
-
"
|
788 |
-
"
|
789 |
-
"
|
790 |
-
"##
|
791 |
-
"
|
792 |
-
"
|
793 |
-
"##
|
794 |
-
"
|
795 |
-
"
|
796 |
-
"##
|
797 |
-
"##
|
798 |
-
"
|
799 |
-
"
|
800 |
-
"
|
801 |
-
"
|
802 |
-
"
|
803 |
-
"
|
804 |
-
"
|
805 |
-
"
|
806 |
-
"
|
807 |
-
"
|
808 |
-
"
|
809 |
-
"
|
810 |
-
"
|
811 |
-
"##
|
812 |
-
"
|
813 |
-
"
|
814 |
-
"
|
815 |
-
"
|
816 |
-
"
|
817 |
-
"
|
818 |
-
"
|
819 |
-
"
|
820 |
-
"
|
821 |
-
"
|
822 |
-
"
|
823 |
-
"
|
824 |
-
"
|
825 |
-
"
|
826 |
-
"##
|
827 |
-
"
|
828 |
-
"
|
829 |
-
"
|
830 |
-
"
|
831 |
-
"
|
832 |
-
"
|
833 |
-
"
|
834 |
-
"
|
835 |
-
"
|
836 |
-
"
|
837 |
-
"
|
838 |
-
"
|
839 |
-
"
|
840 |
-
"
|
841 |
-
"
|
842 |
-
"
|
843 |
-
"
|
844 |
-
"
|
845 |
-
"
|
846 |
-
"
|
847 |
-
"
|
848 |
-
"
|
849 |
-
"
|
850 |
-
"
|
851 |
-
"
|
852 |
-
"
|
853 |
-
"
|
854 |
-
"
|
855 |
-
"
|
856 |
-
"
|
857 |
-
"
|
858 |
-
"
|
859 |
-
"
|
860 |
-
"
|
861 |
-
"
|
862 |
-
"
|
863 |
-
"
|
864 |
-
"
|
865 |
-
"
|
866 |
-
"
|
867 |
-
"##
|
868 |
-
"
|
869 |
-
"
|
870 |
-
"
|
871 |
-
"
|
872 |
-
"
|
873 |
-
"
|
874 |
-
"
|
875 |
-
"
|
876 |
-
"
|
877 |
-
"
|
878 |
-
"
|
879 |
-
"
|
880 |
-
"
|
881 |
-
"
|
882 |
-
"
|
883 |
-
"
|
884 |
-
"
|
885 |
-
"
|
886 |
-
"
|
887 |
-
"
|
888 |
-
"
|
889 |
-
"
|
890 |
-
"
|
891 |
-
"
|
892 |
-
"
|
893 |
-
"
|
894 |
-
"
|
895 |
-
"
|
896 |
-
"
|
897 |
-
"
|
898 |
-
"
|
899 |
-
"
|
900 |
-
"
|
901 |
-
"
|
902 |
-
"
|
903 |
-
"
|
904 |
-
"
|
905 |
-
"
|
906 |
-
"
|
907 |
-
"
|
908 |
-
"
|
909 |
-
"
|
910 |
-
"
|
911 |
-
"
|
912 |
-
"
|
913 |
-
"
|
914 |
-
"
|
915 |
-
"
|
916 |
-
"
|
917 |
-
"
|
918 |
-
"
|
919 |
-
"
|
920 |
-
"
|
921 |
-
"
|
922 |
-
"
|
923 |
-
"
|
924 |
-
"
|
925 |
-
"
|
926 |
-
"
|
927 |
-
"
|
928 |
-
"
|
929 |
-
"
|
930 |
-
"
|
931 |
-
"
|
932 |
-
"
|
933 |
-
"
|
934 |
-
"
|
935 |
-
"
|
936 |
-
"
|
937 |
-
"
|
938 |
-
"
|
939 |
-
"
|
940 |
-
"##
|
941 |
-
"
|
942 |
-
"
|
943 |
-
"
|
944 |
-
"
|
945 |
-
"
|
946 |
-
"
|
947 |
-
"
|
948 |
-
"
|
949 |
-
"
|
950 |
-
"
|
951 |
-
"
|
952 |
-
"
|
953 |
-
"
|
954 |
-
"
|
955 |
-
"
|
956 |
-
"
|
957 |
-
"
|
958 |
-
"
|
959 |
-
"
|
960 |
-
"
|
961 |
-
"
|
962 |
-
"
|
963 |
-
"
|
964 |
-
"
|
965 |
-
"
|
966 |
-
"
|
967 |
-
"
|
968 |
-
"
|
969 |
-
"
|
970 |
-
"##
|
971 |
-
"##
|
972 |
-
"
|
973 |
-
"
|
974 |
-
"
|
975 |
-
"
|
976 |
-
"
|
977 |
-
"
|
978 |
-
"
|
979 |
-
"
|
980 |
-
"
|
981 |
-
"
|
982 |
-
"
|
983 |
-
"
|
984 |
-
"
|
985 |
-
"
|
986 |
-
"
|
987 |
-
"
|
988 |
-
"
|
989 |
-
"
|
990 |
-
"
|
991 |
-
"
|
992 |
-
"
|
993 |
-
"
|
994 |
-
"
|
995 |
-
"
|
996 |
-
"
|
997 |
-
"
|
998 |
-
"
|
999 |
-
"
|
1000 |
-
"##
|
1001 |
-
"
|
1002 |
-
"
|
1003 |
-
"
|
1004 |
-
"
|
1005 |
-
"
|
1006 |
-
"
|
1007 |
-
"
|
1008 |
-
"
|
1009 |
-
"
|
1010 |
-
"
|
1011 |
-
"
|
1012 |
-
"
|
1013 |
-
"
|
1014 |
-
"##
|
1015 |
-
"
|
1016 |
-
"
|
1017 |
-
"
|
1018 |
-
"
|
1019 |
-
"
|
1020 |
-
"
|
1021 |
-
"
|
1022 |
-
"
|
1023 |
-
"
|
1024 |
-
"
|
1025 |
-
"
|
1026 |
-
"
|
1027 |
-
"
|
1028 |
-
"
|
1029 |
-
"
|
1030 |
-
"
|
1031 |
-
"
|
1032 |
-
"
|
1033 |
-
"
|
1034 |
-
"
|
1035 |
-
"
|
1036 |
-
"
|
1037 |
-
"
|
1038 |
-
"
|
1039 |
-
"
|
1040 |
-
"
|
1041 |
-
"
|
1042 |
-
"
|
1043 |
-
"
|
1044 |
-
"
|
1045 |
-
"
|
1046 |
-
"
|
1047 |
-
"
|
1048 |
-
"
|
1049 |
-
"
|
1050 |
-
"
|
1051 |
-
"
|
1052 |
-
"
|
1053 |
-
"
|
1054 |
-
"
|
1055 |
-
"
|
1056 |
-
"
|
1057 |
-
"
|
1058 |
-
"
|
1059 |
-
"
|
1060 |
-
"
|
1061 |
-
"
|
1062 |
-
"
|
1063 |
-
"
|
1064 |
-
"
|
1065 |
-
"
|
1066 |
-
"
|
1067 |
-
"
|
1068 |
-
"
|
1069 |
-
"
|
1070 |
-
"
|
1071 |
-
"
|
1072 |
-
"
|
1073 |
-
"
|
1074 |
-
"
|
1075 |
-
"
|
1076 |
-
"
|
1077 |
-
"
|
1078 |
-
"
|
1079 |
-
"
|
1080 |
-
"
|
1081 |
-
"
|
1082 |
-
"
|
1083 |
-
"
|
1084 |
-
"
|
1085 |
-
"##
|
1086 |
-
"##
|
1087 |
-
"
|
1088 |
-
"
|
1089 |
-
"
|
1090 |
-
"
|
1091 |
-
"
|
1092 |
-
"
|
1093 |
-
"
|
1094 |
-
"
|
1095 |
-
"
|
1096 |
-
"
|
1097 |
-
"
|
1098 |
-
"
|
1099 |
-
"
|
1100 |
-
"
|
1101 |
-
"
|
1102 |
-
"
|
1103 |
-
"
|
1104 |
-
"
|
1105 |
}
|
1106 |
}
|
1107 |
}
|
|
|
14 |
},
|
15 |
{
|
16 |
"id": 1,
|
17 |
+
"content": "[BOS]",
|
18 |
"single_word": false,
|
19 |
"lstrip": false,
|
20 |
"rstrip": false,
|
|
|
23 |
},
|
24 |
{
|
25 |
"id": 2,
|
26 |
+
"content": "[EOS]",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
27 |
"single_word": false,
|
28 |
"lstrip": false,
|
29 |
"rstrip": false,
|
|
|
61 |
}
|
62 |
]
|
63 |
},
|
64 |
+
"post_processor": {
|
65 |
+
"type": "TemplateProcessing",
|
66 |
+
"single": [
|
67 |
+
{
|
68 |
+
"SpecialToken": {
|
69 |
+
"id": "[BOS]",
|
70 |
+
"type_id": 0
|
71 |
+
}
|
72 |
+
},
|
73 |
+
{
|
74 |
+
"Sequence": {
|
75 |
+
"id": "A",
|
76 |
+
"type_id": 0
|
77 |
+
}
|
78 |
+
},
|
79 |
+
{
|
80 |
+
"SpecialToken": {
|
81 |
+
"id": "[EOS]",
|
82 |
+
"type_id": 0
|
83 |
+
}
|
84 |
+
}
|
85 |
+
],
|
86 |
+
"pair": [
|
87 |
+
{
|
88 |
+
"Sequence": {
|
89 |
+
"id": "A",
|
90 |
+
"type_id": 0
|
91 |
+
}
|
92 |
+
},
|
93 |
+
{
|
94 |
+
"Sequence": {
|
95 |
+
"id": "B",
|
96 |
+
"type_id": 1
|
97 |
+
}
|
98 |
+
}
|
99 |
+
],
|
100 |
+
"special_tokens": {
|
101 |
+
"[BOS]": {
|
102 |
+
"id": "[BOS]",
|
103 |
+
"ids": [
|
104 |
+
1
|
105 |
+
],
|
106 |
+
"tokens": [
|
107 |
+
"[BOS]"
|
108 |
+
]
|
109 |
+
},
|
110 |
+
"[EOS]": {
|
111 |
+
"id": "[EOS]",
|
112 |
+
"ids": [
|
113 |
+
2
|
114 |
+
],
|
115 |
+
"tokens": [
|
116 |
+
"[EOS]"
|
117 |
+
]
|
118 |
+
}
|
119 |
+
}
|
120 |
+
},
|
121 |
"decoder": null,
|
122 |
"model": {
|
123 |
"type": "WordPiece",
|
|
|
126 |
"max_input_chars_per_word": 100,
|
127 |
"vocab": {
|
128 |
"[UNK]": 0,
|
129 |
+
"[BOS]": 1,
|
130 |
+
"[EOS]": 2,
|
131 |
+
"!": 3,
|
132 |
+
"\"": 4,
|
133 |
+
"#": 5,
|
134 |
+
"$": 6,
|
135 |
+
"%": 7,
|
136 |
+
"&": 8,
|
137 |
+
"'": 9,
|
138 |
+
"(": 10,
|
139 |
+
")": 11,
|
140 |
+
"*": 12,
|
141 |
+
"+": 13,
|
142 |
+
",": 14,
|
143 |
+
"-": 15,
|
144 |
+
".": 16,
|
145 |
+
"/": 17,
|
146 |
+
"0": 18,
|
147 |
+
"1": 19,
|
148 |
+
"2": 20,
|
149 |
+
"3": 21,
|
150 |
+
"4": 22,
|
151 |
+
"5": 23,
|
152 |
+
"6": 24,
|
153 |
+
"7": 25,
|
154 |
+
"8": 26,
|
155 |
+
"9": 27,
|
156 |
+
":": 28,
|
157 |
+
";": 29,
|
158 |
+
"<": 30,
|
159 |
+
"=": 31,
|
160 |
+
">": 32,
|
161 |
+
"?": 33,
|
162 |
+
"@": 34,
|
163 |
+
"[": 35,
|
164 |
+
"\\": 36,
|
165 |
+
"]": 37,
|
166 |
+
"_": 38,
|
167 |
+
"`": 39,
|
168 |
+
"a": 40,
|
169 |
+
"b": 41,
|
170 |
+
"c": 42,
|
171 |
+
"d": 43,
|
172 |
+
"e": 44,
|
173 |
+
"f": 45,
|
174 |
+
"g": 46,
|
175 |
+
"h": 47,
|
176 |
+
"i": 48,
|
177 |
+
"j": 49,
|
178 |
+
"k": 50,
|
179 |
+
"l": 51,
|
180 |
+
"m": 52,
|
181 |
+
"n": 53,
|
182 |
+
"o": 54,
|
183 |
+
"p": 55,
|
184 |
+
"q": 56,
|
185 |
+
"r": 57,
|
186 |
+
"s": 58,
|
187 |
+
"t": 59,
|
188 |
+
"u": 60,
|
189 |
+
"v": 61,
|
190 |
+
"w": 62,
|
191 |
+
"x": 63,
|
192 |
+
"y": 64,
|
193 |
+
"z": 65,
|
194 |
+
"{": 66,
|
195 |
+
"|": 67,
|
196 |
+
"}": 68,
|
197 |
+
"~": 69,
|
198 |
+
"##e": 70,
|
199 |
+
"##n": 71,
|
200 |
+
"##t": 72,
|
201 |
+
"##l": 73,
|
202 |
+
"##a": 74,
|
203 |
+
"##m": 75,
|
204 |
+
"##s": 76,
|
205 |
+
"##u": 77,
|
206 |
+
"##k": 78,
|
207 |
+
"##o": 79,
|
208 |
+
"##r": 80,
|
209 |
+
"##d": 81,
|
210 |
+
"##f": 82,
|
211 |
+
"##b": 83,
|
212 |
+
"##y": 84,
|
213 |
+
"##i": 85,
|
214 |
+
"##p": 86,
|
215 |
+
"##v": 87,
|
216 |
+
"##g": 88,
|
217 |
+
"##h": 89,
|
218 |
+
"##c": 90,
|
219 |
+
"##w": 91,
|
220 |
+
"##z": 92,
|
221 |
+
"##q": 93,
|
222 |
"##j": 94,
|
223 |
+
"##x": 95,
|
224 |
+
"##he": 96,
|
225 |
+
"the": 97,
|
226 |
+
"##nd": 98,
|
227 |
+
"##ed": 99,
|
228 |
+
"and": 100,
|
229 |
+
"to": 101,
|
230 |
+
"##er": 102,
|
231 |
+
"wa": 103,
|
232 |
+
"##ou": 104,
|
233 |
+
"##in": 105,
|
234 |
+
"he": 106,
|
235 |
+
"##re": 107,
|
236 |
+
"was": 108,
|
237 |
+
"sa": 109,
|
238 |
+
"##ing": 110,
|
239 |
+
"##om": 111,
|
240 |
+
"she": 112,
|
241 |
+
"##ar": 113,
|
242 |
+
"##il": 114,
|
243 |
+
"##it": 115,
|
244 |
+
"##ay": 116,
|
245 |
+
"it": 117,
|
246 |
+
"##id": 118,
|
247 |
+
"##at": 119,
|
248 |
+
"they": 120,
|
249 |
+
"ha": 121,
|
250 |
+
"##en": 122,
|
251 |
+
"##is": 123,
|
252 |
+
"##an": 124,
|
253 |
+
"th": 125,
|
254 |
+
"on": 126,
|
255 |
+
"##or": 127,
|
256 |
+
"##im": 128,
|
257 |
+
"##on": 129,
|
258 |
+
"##ut": 130,
|
259 |
+
"her": 131,
|
260 |
+
"##ll": 132,
|
261 |
+
"##le": 133,
|
262 |
+
"##et": 134,
|
263 |
+
"##ot": 135,
|
264 |
+
"##ir": 136,
|
265 |
+
"##es": 137,
|
266 |
+
"in": 138,
|
267 |
+
"##ow": 139,
|
268 |
+
"you": 140,
|
269 |
+
"##ck": 141,
|
270 |
+
"##ld": 142,
|
271 |
+
"##oo": 143,
|
272 |
+
"said": 144,
|
273 |
+
"be": 145,
|
274 |
+
"##ily": 146,
|
275 |
+
"st": 147,
|
276 |
+
"##ig": 148,
|
277 |
+
"tim": 149,
|
278 |
+
"so": 150,
|
279 |
+
"##ce": 151,
|
280 |
+
"##pp": 152,
|
281 |
+
"wit": 153,
|
282 |
+
"his": 154,
|
283 |
+
"with": 155,
|
284 |
+
"mom": 156,
|
285 |
+
"##ve": 157,
|
286 |
+
"lily": 158,
|
287 |
+
"of": 159,
|
288 |
+
"##ked": 160,
|
289 |
+
"fr": 161,
|
290 |
+
"that": 162,
|
291 |
+
"pl": 163,
|
292 |
+
"##ery": 164,
|
293 |
+
"##am": 165,
|
294 |
+
"##ad": 166,
|
295 |
+
"##ke": 167,
|
296 |
+
"##nt": 168,
|
297 |
+
"but": 169,
|
298 |
+
"day": 170,
|
299 |
+
"up": 171,
|
300 |
+
"##ie": 172,
|
301 |
+
"play": 173,
|
302 |
+
"had": 174,
|
303 |
+
"##el": 175,
|
304 |
+
"wh": 176,
|
305 |
+
"for": 177,
|
306 |
+
"##st": 178,
|
307 |
+
"##un": 179,
|
308 |
+
"##ould": 180,
|
309 |
+
"an": 181,
|
310 |
+
"##my": 182,
|
311 |
+
"##ent": 183,
|
312 |
+
"li": 184,
|
313 |
+
"##ra": 185,
|
314 |
+
"##ch": 186,
|
315 |
+
"do": 187,
|
316 |
+
"happ": 188,
|
317 |
+
"one": 189,
|
318 |
+
"sh": 190,
|
319 |
+
"want": 191,
|
320 |
+
"##itt": 192,
|
321 |
+
"##her": 193,
|
322 |
+
"not": 194,
|
323 |
+
"there": 195,
|
324 |
+
"##ly": 196,
|
325 |
+
"##ome": 197,
|
326 |
+
"very": 198,
|
327 |
+
"##se": 199,
|
328 |
+
"##ound": 200,
|
329 |
+
"as": 201,
|
330 |
+
"ba": 202,
|
331 |
+
"litt": 203,
|
332 |
+
"little": 204,
|
333 |
+
"ne": 205,
|
334 |
+
"time": 206,
|
335 |
+
"##ht": 207,
|
336 |
+
"##al": 208,
|
337 |
+
"ma": 209,
|
338 |
+
"sm": 210,
|
339 |
+
"happy": 211,
|
340 |
+
"is": 212,
|
341 |
+
"big": 213,
|
342 |
+
"loo": 214,
|
343 |
+
"saw": 215,
|
344 |
+
"##iend": 216,
|
345 |
+
"friend": 217,
|
346 |
+
"##ry": 218,
|
347 |
+
"re": 219,
|
348 |
+
"bo": 220,
|
349 |
+
"##ur": 221,
|
350 |
+
"##ter": 222,
|
351 |
+
"##ug": 223,
|
352 |
+
"##ere": 224,
|
353 |
+
"##ved": 225,
|
354 |
+
"lo": 226,
|
355 |
+
"were": 227,
|
356 |
+
"once": 228,
|
357 |
+
"##ore": 229,
|
358 |
+
"se": 230,
|
359 |
+
"ev": 231,
|
360 |
+
"go": 232,
|
361 |
+
"sp": 233,
|
362 |
+
"him": 234,
|
363 |
+
"too": 235,
|
364 |
+
"ca": 236,
|
365 |
+
"##ide": 237,
|
366 |
+
"we": 238,
|
367 |
+
"are": 239,
|
368 |
+
"tom": 240,
|
369 |
+
"at": 241,
|
370 |
+
"can": 242,
|
371 |
+
"##irl": 243,
|
372 |
+
"##ard": 244,
|
373 |
+
"wanted": 245,
|
374 |
+
"whe": 246,
|
375 |
+
"ben": 247,
|
376 |
+
"##ill": 248,
|
377 |
+
"girl": 249,
|
378 |
+
"upon": 250,
|
379 |
+
"##ec": 251,
|
380 |
+
"their": 252,
|
381 |
+
"out": 253,
|
382 |
+
"them": 254,
|
383 |
+
"##ys": 255,
|
384 |
+
"##fu": 256,
|
385 |
+
"##way": 257,
|
386 |
+
"did": 258,
|
387 |
+
"smil": 259,
|
388 |
+
"##ind": 260,
|
389 |
+
"could": 261,
|
390 |
+
"have": 262,
|
391 |
+
"no": 263,
|
392 |
+
"##ri": 264,
|
393 |
+
"##ted": 265,
|
394 |
+
"##ver": 266,
|
395 |
+
"##ain": 267,
|
396 |
+
"ex": 268,
|
397 |
+
"##hed": 269,
|
398 |
+
"all": 270,
|
399 |
+
"ar": 271,
|
400 |
+
"went": 272,
|
401 |
+
"hel": 273,
|
402 |
+
"su": 274,
|
403 |
+
"##ic": 275,
|
404 |
+
"when": 276,
|
405 |
+
"ta": 277,
|
406 |
+
"help": 278,
|
407 |
+
"##ful": 279,
|
408 |
+
"##ood": 280,
|
409 |
+
"friends": 281,
|
410 |
+
"##hing": 282,
|
411 |
+
"nam": 283,
|
412 |
+
"##ight": 284,
|
413 |
+
"what": 285,
|
414 |
+
"kn": 286,
|
415 |
+
"le": 287,
|
416 |
+
"##um": 288,
|
417 |
+
"back": 289,
|
418 |
+
"##ark": 290,
|
419 |
+
"##one": 291,
|
420 |
+
"cl": 292,
|
421 |
+
"from": 293,
|
422 |
+
"fun": 294,
|
423 |
+
"al": 295,
|
424 |
+
"then": 296,
|
425 |
+
"##all": 297,
|
426 |
+
"timmy": 298,
|
427 |
+
"ro": 299,
|
428 |
+
"star": 300,
|
429 |
+
"every": 301,
|
430 |
+
"sc": 302,
|
431 |
+
"smiled": 303,
|
432 |
+
"named": 304,
|
433 |
+
"##oug": 305,
|
434 |
+
"loved": 306,
|
435 |
+
"##side": 307,
|
436 |
+
"man": 308,
|
437 |
+
"some": 309,
|
438 |
+
"##elt": 310,
|
439 |
+
"asked": 311,
|
440 |
+
"see": 312,
|
441 |
+
"me": 313,
|
442 |
+
"##ick": 314,
|
443 |
+
"like": 315,
|
444 |
+
"fe": 316,
|
445 |
+
"##op": 317,
|
446 |
+
"felt": 318,
|
447 |
+
"br": 319,
|
448 |
+
"looked": 320,
|
449 |
+
"around": 321,
|
450 |
+
"look": 322,
|
451 |
+
"##ep": 323,
|
452 |
+
"##ame": 324,
|
453 |
+
"##omet": 325,
|
454 |
+
"would": 326,
|
455 |
+
"bir": 327,
|
456 |
+
"somet": 328,
|
457 |
+
"##get": 329,
|
458 |
+
"fa": 330,
|
459 |
+
"##ong": 331,
|
460 |
+
"boy": 332,
|
461 |
+
"##ss": 333,
|
462 |
+
"bird": 334,
|
463 |
+
"pr": 335,
|
464 |
+
"##dd": 336,
|
465 |
+
"jo": 337,
|
466 |
+
"##est": 338,
|
467 |
+
"##ings": 339,
|
468 |
+
"ag": 340,
|
469 |
+
"wor": 341,
|
470 |
+
"mommy": 342,
|
471 |
+
"make": 343,
|
472 |
+
"##ade": 344,
|
473 |
+
"than": 345,
|
474 |
+
"car": 346,
|
475 |
+
"##own": 347,
|
476 |
+
"tre": 348,
|
477 |
+
"ran": 349,
|
478 |
+
"##gether": 350,
|
479 |
+
"together": 351,
|
480 |
+
"la": 352,
|
481 |
+
"away": 353,
|
482 |
+
"dad": 354,
|
483 |
+
"says": 355,
|
484 |
+
"started": 356,
|
485 |
+
"##ice": 357,
|
486 |
+
"##oud": 358,
|
487 |
+
"something": 359,
|
488 |
+
"##ared": 360,
|
489 |
+
"made": 361,
|
490 |
+
"co": 362,
|
491 |
+
"fl": 363,
|
492 |
+
"##ther": 364,
|
493 |
+
"##ited": 365,
|
494 |
+
"park": 366,
|
495 |
+
"sad": 367,
|
496 |
+
"good": 368,
|
497 |
+
"##ack": 369,
|
498 |
+
"other": 370,
|
499 |
+
"ch": 371,
|
500 |
+
"exc": 372,
|
501 |
+
"new": 373,
|
502 |
+
"put": 374,
|
503 |
+
"who": 375,
|
504 |
+
"##out": 376,
|
505 |
+
"let": 377,
|
506 |
+
"hug": 378,
|
507 |
+
"mu": 379,
|
508 |
+
"##ble": 380,
|
509 |
+
"again": 381,
|
510 |
+
"home": 382,
|
511 |
+
"sam": 383,
|
512 |
+
"found": 384,
|
513 |
+
"dec": 385,
|
514 |
+
"##pped": 386,
|
515 |
+
"##ried": 387,
|
516 |
+
"wal": 388,
|
517 |
+
"##ure": 389,
|
518 |
+
"get": 390,
|
519 |
+
"##ach": 391,
|
520 |
+
"playing": 392,
|
521 |
+
"##ought": 393,
|
522 |
+
"gra": 394,
|
523 |
+
"##na": 395,
|
524 |
+
"##pl": 396,
|
525 |
+
"sw": 397,
|
526 |
+
"##ous": 398,
|
527 |
+
"things": 399,
|
528 |
+
"bl": 400,
|
529 |
+
"excited": 401,
|
530 |
+
"your": 402,
|
531 |
+
"liked": 403,
|
532 |
+
"got": 404,
|
533 |
+
"##ny": 405,
|
534 |
+
"##uck": 406,
|
535 |
+
"##king": 407,
|
536 |
+
"##ge": 408,
|
537 |
+
"##ided": 409,
|
538 |
+
"decided": 410,
|
539 |
+
"came": 411,
|
540 |
+
"my": 412,
|
541 |
+
"dog": 413,
|
542 |
+
"this": 414,
|
543 |
+
"scared": 415,
|
544 |
+
"##ust": 416,
|
545 |
+
"down": 417,
|
546 |
+
"bec": 418,
|
547 |
+
"##ouse": 419,
|
548 |
+
"ab": 420,
|
549 |
+
"find": 421,
|
550 |
+
"pa": 422,
|
551 |
+
"care": 423,
|
552 |
+
"will": 424,
|
553 |
+
"po": 425,
|
554 |
+
"sara": 426,
|
555 |
+
"gr": 427,
|
556 |
+
"feel": 428,
|
557 |
+
"anna": 429,
|
558 |
+
"##ell": 430,
|
559 |
+
"max": 431,
|
560 |
+
"##as": 432,
|
561 |
+
"##ist": 433,
|
562 |
+
"bu": 434,
|
563 |
+
"##arn": 435,
|
564 |
+
"##ave": 436,
|
565 |
+
"##nder": 437,
|
566 |
+
"##ways": 438,
|
567 |
+
"##ess": 439,
|
568 |
+
"always": 440,
|
569 |
+
"mo": 441,
|
570 |
+
"took": 442,
|
571 |
+
"about": 443,
|
572 |
+
"##ers": 444,
|
573 |
+
"lot": 445,
|
574 |
+
"##ook": 446,
|
575 |
+
"toys": 447,
|
576 |
+
"kne": 448,
|
577 |
+
"didn": 449,
|
578 |
+
"##ged": 450,
|
579 |
+
"##ise": 451,
|
580 |
+
"##bb": 452,
|
581 |
+
"old": 453,
|
582 |
+
"outside": 454,
|
583 |
+
"tree": 455,
|
584 |
+
"ho": 456,
|
585 |
+
"##ite": 457,
|
586 |
+
"how": 458,
|
587 |
+
"##ally": 459,
|
588 |
+
"ball": 460,
|
589 |
+
"thought": 461,
|
590 |
+
"##ant": 462,
|
591 |
+
"sor": 463,
|
592 |
+
"af": 464,
|
593 |
+
"more": 465,
|
594 |
+
"##ma": 466,
|
595 |
+
"##eci": 467,
|
596 |
+
"##ened": 468,
|
597 |
+
"##ched": 469,
|
598 |
+
"learn": 470,
|
599 |
+
"##ret": 471,
|
600 |
+
"pu": 472,
|
601 |
+
"tw": 473,
|
602 |
+
"know": 474,
|
603 |
+
"cat": 475,
|
604 |
+
"##to": 476,
|
605 |
+
"take": 477,
|
606 |
+
"don": 478,
|
607 |
+
"mi": 479,
|
608 |
+
"laug": 480,
|
609 |
+
"pe": 481,
|
610 |
+
"speci": 482,
|
611 |
+
"special": 483,
|
612 |
+
"sudd": 484,
|
613 |
+
"sudden": 485,
|
614 |
+
"inside": 486,
|
615 |
+
"knew": 487,
|
616 |
+
"##ty": 488,
|
617 |
+
"sorry": 489,
|
618 |
+
"##ive": 490,
|
619 |
+
"##ro": 491,
|
620 |
+
"any": 492,
|
621 |
+
"jack": 493,
|
622 |
+
"##ff": 494,
|
623 |
+
"suddenly": 495,
|
624 |
+
"just": 496,
|
625 |
+
"toy": 497,
|
626 |
+
"##ue": 498,
|
627 |
+
"after": 499,
|
628 |
+
"tr": 500,
|
629 |
+
"if": 501,
|
630 |
+
"show": 502,
|
631 |
+
"##ink": 503,
|
632 |
+
"##lly": 504,
|
633 |
+
"or": 505,
|
634 |
+
"run": 506,
|
635 |
+
"ra": 507,
|
636 |
+
"sl": 508,
|
637 |
+
"much": 509,
|
638 |
+
"##ish": 510,
|
639 |
+
"hand": 511,
|
640 |
+
"yes": 512,
|
641 |
+
"house": 513,
|
642 |
+
"sun": 514,
|
643 |
+
"op": 515,
|
644 |
+
"sk": 516,
|
645 |
+
"clo": 517,
|
646 |
+
"into": 518,
|
647 |
+
"fin": 519,
|
648 |
+
"tried": 520,
|
649 |
+
"en": 521,
|
650 |
+
"water": 522,
|
651 |
+
"##ate": 523,
|
652 |
+
"told": 524,
|
653 |
+
"each": 525,
|
654 |
+
"##ea": 526,
|
655 |
+
"over": 527,
|
656 |
+
"proud": 528,
|
657 |
+
"##ump": 529,
|
658 |
+
"gave": 530,
|
659 |
+
"heard": 531,
|
660 |
+
"never": 532,
|
661 |
+
"ok": 533,
|
662 |
+
"##dy": 534,
|
663 |
+
"##by": 535,
|
664 |
+
"thank": 536,
|
665 |
+
"##use": 537,
|
666 |
+
"eat": 538,
|
667 |
+
"room": 539,
|
668 |
+
"expl": 540,
|
669 |
+
"##other": 541,
|
670 |
+
"pick": 542,
|
671 |
+
"pret": 543,
|
672 |
+
"qu": 544,
|
673 |
+
"##lled": 545,
|
674 |
+
"gre": 546,
|
675 |
+
"come": 547,
|
676 |
+
"couldn": 548,
|
677 |
+
"played": 549,
|
678 |
+
"##ion": 550,
|
679 |
+
"mia": 551,
|
680 |
+
"sha": 552,
|
681 |
+
"##ause": 553,
|
682 |
+
"because": 554,
|
683 |
+
"wat": 555,
|
684 |
+
"hugged": 556,
|
685 |
+
"##ious": 557,
|
686 |
+
"off": 558,
|
687 |
+
"bear": 559,
|
688 |
+
"now": 560,
|
689 |
+
"com": 561,
|
690 |
+
"nice": 562,
|
691 |
+
"fo": 563,
|
692 |
+
"##oth": 564,
|
693 |
+
"box": 565,
|
694 |
+
"##our": 566,
|
695 |
+
"str": 567,
|
696 |
+
"need": 568,
|
697 |
+
"bet": 569,
|
698 |
+
"many": 570,
|
699 |
+
"##ile": 571,
|
700 |
+
"##fe": 572,
|
701 |
+
"##ft": 573,
|
702 |
+
"small": 574,
|
703 |
+
"##eep": 575,
|
704 |
+
"long": 576,
|
705 |
+
"##ving": 577,
|
706 |
+
"##kes": 578,
|
707 |
+
"##sed": 579,
|
708 |
+
"##gry": 580,
|
709 |
+
"anim": 581,
|
710 |
+
"animal": 582,
|
711 |
+
"try": 583,
|
712 |
+
"end": 584,
|
713 |
+
"##ough": 585,
|
714 |
+
"unt": 586,
|
715 |
+
"##cy": 587,
|
716 |
+
"##ild": 588,
|
717 |
+
"until": 589,
|
718 |
+
"even": 590,
|
719 |
+
"##urt": 591,
|
720 |
+
"##ort": 592,
|
721 |
+
"##elf": 593,
|
722 |
+
"soon": 594,
|
723 |
+
"##iz": 595,
|
724 |
+
"kind": 596,
|
725 |
+
"love": 597,
|
726 |
+
"learned": 598,
|
727 |
+
"bea": 599,
|
728 |
+
"everyone": 600,
|
729 |
+
"by": 601,
|
730 |
+
"ad": 602,
|
731 |
+
"better": 603,
|
732 |
+
"flow": 604,
|
733 |
+
"spot": 605,
|
734 |
+
"##ine": 606,
|
735 |
+
"best": 607,
|
736 |
+
"##urp": 608,
|
737 |
+
"say": 609,
|
738 |
+
"##mp": 610,
|
739 |
+
"##ady": 611,
|
740 |
+
"##ream": 612,
|
741 |
+
"cle": 613,
|
742 |
+
"##urn": 614,
|
743 |
+
"##ace": 615,
|
744 |
+
"##ves": 616,
|
745 |
+
"fi": 617,
|
746 |
+
"gard": 618,
|
747 |
+
"garden": 619,
|
748 |
+
"fast": 620,
|
749 |
+
"its": 621,
|
750 |
+
"che": 622,
|
751 |
+
"careful": 623,
|
752 |
+
"##ber": 624,
|
753 |
+
"beaut": 625,
|
754 |
+
"##ies": 626,
|
755 |
+
"bra": 627,
|
756 |
+
"thanked": 628,
|
757 |
+
"sky": 629,
|
758 |
+
"laughed": 630,
|
759 |
+
"jump": 631,
|
760 |
+
"gl": 632,
|
761 |
+
"loud": 633,
|
762 |
+
"sn": 634,
|
763 |
+
"list": 635,
|
764 |
+
"ow": 636,
|
765 |
+
"##ear": 637,
|
766 |
+
"##ct": 638,
|
767 |
+
"##iny": 639,
|
768 |
+
"wo": 640,
|
769 |
+
"beauti": 641,
|
770 |
+
"##sh": 642,
|
771 |
+
"##lew": 643,
|
772 |
+
"lots": 644,
|
773 |
+
"beautiful": 645,
|
774 |
+
"hard": 646,
|
775 |
+
"still": 647,
|
776 |
+
"animals": 648,
|
777 |
+
"fam": 649,
|
778 |
+
"joh": 650,
|
779 |
+
"under": 651,
|
780 |
+
"john": 652,
|
781 |
+
"lu": 653,
|
782 |
+
"mum": 654,
|
783 |
+
"stay": 655,
|
784 |
+
"hurt": 656,
|
785 |
+
"##ning": 657,
|
786 |
+
"both": 658,
|
787 |
+
"dan": 659,
|
788 |
+
"##ree": 660,
|
789 |
+
"##self": 661,
|
790 |
+
"way": 662,
|
791 |
+
"rem": 663,
|
792 |
+
"two": 664,
|
793 |
+
"##hes": 665,
|
794 |
+
"bad": 666,
|
795 |
+
"safe": 667,
|
796 |
+
"col": 668,
|
797 |
+
"##ool": 669,
|
798 |
+
"##be": 670,
|
799 |
+
"di": 671,
|
800 |
+
"red": 672,
|
801 |
+
"book": 673,
|
802 |
+
"imp": 674,
|
803 |
+
"tow": 675,
|
804 |
+
"##ople": 676,
|
805 |
+
"##ane": 677,
|
806 |
+
"lived": 678,
|
807 |
+
"people": 679,
|
808 |
+
"okay": 680,
|
809 |
+
"##em": 681,
|
810 |
+
"lucy": 682,
|
811 |
+
"walked": 683,
|
812 |
+
"should": 684,
|
813 |
+
"brave": 685,
|
814 |
+
"surp": 686,
|
815 |
+
"surpr": 687,
|
816 |
+
"##ase": 688,
|
817 |
+
"##ock": 689,
|
818 |
+
"##ished": 690,
|
819 |
+
"angry": 691,
|
820 |
+
"family": 692,
|
821 |
+
"adv": 693,
|
822 |
+
"##ress": 694,
|
823 |
+
"##igh": 695,
|
824 |
+
"flew": 696,
|
825 |
+
"called": 697,
|
826 |
+
"stor": 698,
|
827 |
+
"##ept": 699,
|
828 |
+
"##ip": 700,
|
829 |
+
"##eet": 701,
|
830 |
+
"sure": 702,
|
831 |
+
"##led": 703,
|
832 |
+
"fore": 704,
|
833 |
+
"kept": 705,
|
834 |
+
"fly": 706,
|
835 |
+
"share": 707,
|
836 |
+
"##ect": 708,
|
837 |
+
"##fore": 709,
|
838 |
+
"before": 710,
|
839 |
+
"##ger": 711,
|
840 |
+
"##art": 712,
|
841 |
+
"while": 713,
|
842 |
+
"##xt": 714,
|
843 |
+
"##ised": 715,
|
844 |
+
"##dded": 716,
|
845 |
+
"pic": 717,
|
846 |
+
"keep": 718,
|
847 |
+
"door": 719,
|
848 |
+
"going": 720,
|
849 |
+
"pretty": 721,
|
850 |
+
"rock": 722,
|
851 |
+
"clean": 723,
|
852 |
+
"dra": 724,
|
853 |
+
"next": 725,
|
854 |
+
"why": 726,
|
855 |
+
"may": 727,
|
856 |
+
"advent": 728,
|
857 |
+
"##ied": 729,
|
858 |
+
"##ary": 730,
|
859 |
+
"give": 731,
|
860 |
+
"noise": 732,
|
861 |
+
"con": 733,
|
862 |
+
"opened": 734,
|
863 |
+
"shiny": 735,
|
864 |
+
"far": 736,
|
865 |
+
"un": 737,
|
866 |
+
"doll": 738,
|
867 |
+
"wind": 739,
|
868 |
+
"id": 740,
|
869 |
+
"cry": 741,
|
870 |
+
"grand": 742,
|
871 |
+
"real": 743,
|
872 |
+
"##illy": 744,
|
873 |
+
"##end": 745,
|
874 |
+
"sto": 746,
|
875 |
+
"##so": 747,
|
876 |
+
"turn": 748,
|
877 |
+
"explore": 749,
|
878 |
+
"ground": 750,
|
879 |
+
"also": 751,
|
880 |
+
"##les": 752,
|
881 |
+
"ey": 753,
|
882 |
+
"##ner": 754,
|
883 |
+
"idea": 755,
|
884 |
+
"color": 756,
|
885 |
+
"##ap": 757,
|
886 |
+
"where": 758,
|
887 |
+
"nodded": 759,
|
888 |
+
"war": 760,
|
889 |
+
"feeling": 761,
|
890 |
+
"blue": 762,
|
891 |
+
"bob": 763,
|
892 |
+
"picked": 764,
|
893 |
+
"##imb": 765,
|
894 |
+
"walking": 766,
|
895 |
+
"clos": 767,
|
896 |
+
"##thing": 768,
|
897 |
+
"climb": 769,
|
898 |
+
"thr": 770,
|
899 |
+
"##ting": 771,
|
900 |
+
"has": 772,
|
901 |
+
"ple": 773,
|
902 |
+
"wait": 774,
|
903 |
+
"bed": 775,
|
904 |
+
"smile": 776,
|
905 |
+
"adventure": 777,
|
906 |
+
"##oy": 778,
|
907 |
+
"being": 779,
|
908 |
+
"##th": 780,
|
909 |
+
"maybe": 781,
|
910 |
+
"finally": 782,
|
911 |
+
"looking": 783,
|
912 |
+
"da": 784,
|
913 |
+
"##iced": 785,
|
914 |
+
"##ture": 786,
|
915 |
+
"diff": 787,
|
916 |
+
"wr": 788,
|
917 |
+
"##and": 789,
|
918 |
+
"food": 790,
|
919 |
+
"listen": 791,
|
920 |
+
"##joy": 792,
|
921 |
+
"picture": 793,
|
922 |
+
"think": 794,
|
923 |
+
"remem": 795,
|
924 |
+
"del": 796,
|
925 |
+
"truck": 797,
|
926 |
+
"tra": 798,
|
927 |
+
"eyes": 799,
|
928 |
+
"##ught": 800,
|
929 |
+
"bro": 801,
|
930 |
+
"gi": 802,
|
931 |
+
"repl": 803,
|
932 |
+
"stopped": 804,
|
933 |
+
"here": 805,
|
934 |
+
"great": 806,
|
935 |
+
"bre": 807,
|
936 |
+
"ru": 808,
|
937 |
+
"vo": 809,
|
938 |
+
"walk": 810,
|
939 |
+
"##qu": 811,
|
940 |
+
"year": 812,
|
941 |
+
"enjoy": 813,
|
942 |
+
"wonder": 814,
|
943 |
+
"remember": 815,
|
944 |
+
"##able": 816,
|
945 |
+
"hands": 817,
|
946 |
+
"sue": 818,
|
947 |
+
"quick": 819,
|
948 |
+
"##per": 820,
|
949 |
+
"ever": 821,
|
950 |
+
"cur": 822,
|
951 |
+
"head": 823,
|
952 |
+
"flowers": 824,
|
953 |
+
"import": 825,
|
954 |
+
"forest": 826,
|
955 |
+
"##og": 827,
|
956 |
+
"ac": 828,
|
957 |
+
"noticed": 829,
|
958 |
+
"near": 830,
|
959 |
+
"##bbit": 831,
|
960 |
+
"app": 832,
|
961 |
+
"dis": 833,
|
962 |
+
"##ized": 834,
|
963 |
+
"watch": 835,
|
964 |
+
"##irst": 836,
|
965 |
+
"rabbit": 837,
|
966 |
+
"fish": 838,
|
967 |
+
"##llow": 839,
|
968 |
+
"important": 840,
|
969 |
+
"##age": 841,
|
970 |
+
"ama": 842,
|
971 |
+
"us": 843,
|
972 |
+
"rain": 844,
|
973 |
+
"sound": 845,
|
974 |
+
"slide": 846,
|
975 |
+
"bun": 847,
|
976 |
+
"amaz": 848,
|
977 |
+
"replied": 849,
|
978 |
+
"stop": 850,
|
979 |
+
"work": 851,
|
980 |
+
"follow": 852,
|
981 |
+
"mor": 853,
|
982 |
+
"showed": 854,
|
983 |
+
"tal": 855,
|
984 |
+
"mean": 856,
|
985 |
+
"tou": 857,
|
986 |
+
"##ces": 858,
|
987 |
+
"##gan": 859,
|
988 |
+
"right": 860,
|
989 |
+
"sarah": 861,
|
990 |
+
"ask": 862,
|
991 |
+
"##bbed": 863,
|
992 |
+
"differ": 864,
|
993 |
+
"mag": 865,
|
994 |
+
"goodby": 866,
|
995 |
+
"our": 867,
|
996 |
+
"bright": 868,
|
997 |
+
"##day": 869,
|
998 |
+
"watched": 870,
|
999 |
+
"goodbye": 871,
|
1000 |
+
"hop": 872,
|
1001 |
+
"please": 873,
|
1002 |
+
"use": 874,
|
1003 |
+
"strong": 875,
|
1004 |
+
"am": 876,
|
1005 |
+
"stick": 877,
|
1006 |
+
"quickly": 878,
|
1007 |
+
"daddy": 879,
|
1008 |
+
"been": 880,
|
1009 |
+
"voice": 881,
|
1010 |
+
"yell": 882,
|
1011 |
+
"##ath": 883,
|
1012 |
+
"jane": 884,
|
1013 |
+
"different": 885,
|
1014 |
+
"child": 886,
|
1015 |
+
"boat": 887,
|
1016 |
+
"##llo": 888,
|
1017 |
+
"##co": 889,
|
1018 |
+
"##che": 890,
|
1019 |
+
"hello": 891,
|
1020 |
+
"first": 892,
|
1021 |
+
"became": 893,
|
1022 |
+
"face": 894,
|
1023 |
+
"place": 895,
|
1024 |
+
"##ange": 896,
|
1025 |
+
"does": 897,
|
1026 |
+
"high": 898,
|
1027 |
+
"##ng": 899,
|
1028 |
+
"store": 900,
|
1029 |
+
"closer": 901,
|
1030 |
+
"curious": 902,
|
1031 |
+
"##ak": 903,
|
1032 |
+
"warm": 904,
|
1033 |
+
"sand": 905,
|
1034 |
+
"dress": 906,
|
1035 |
+
"bel": 907,
|
1036 |
+
"##ummy": 908,
|
1037 |
+
"joe": 909,
|
1038 |
+
"cook": 910,
|
1039 |
+
"tell": 911,
|
1040 |
+
"##ila": 912,
|
1041 |
+
"forg": 913,
|
1042 |
+
"em": 914,
|
1043 |
+
"three": 915,
|
1044 |
+
"fav": 916,
|
1045 |
+
"grandma": 917,
|
1046 |
+
"##oon": 918,
|
1047 |
+
"##ount": 919,
|
1048 |
+
"open": 920,
|
1049 |
+
"lila": 921,
|
1050 |
+
"##leep": 922,
|
1051 |
+
"night": 923,
|
1052 |
+
"cake": 924,
|
1053 |
+
"block": 925,
|
1054 |
+
"##more": 926,
|
1055 |
+
"pie": 927,
|
1056 |
+
"anymore": 928,
|
1057 |
+
"bunny": 929,
|
1058 |
+
"butter": 930,
|
1059 |
+
"mon": 931,
|
1060 |
+
"##iss": 932,
|
1061 |
+
"##ached": 933,
|
1062 |
+
"lea": 934,
|
1063 |
+
"sweet": 935,
|
1064 |
+
"##ired": 936,
|
1065 |
+
"kid": 937,
|
1066 |
+
"##ull": 938,
|
1067 |
+
"only": 939,
|
1068 |
+
"flo": 940,
|
1069 |
+
"kit": 941,
|
1070 |
+
"pain": 942,
|
1071 |
+
"grabbed": 943,
|
1072 |
+
"duck": 944,
|
1073 |
+
"##isy": 945,
|
1074 |
+
"fell": 946,
|
1075 |
+
"birds": 947,
|
1076 |
+
"fire": 948,
|
1077 |
+
"cont": 949,
|
1078 |
+
"##ered": 950,
|
1079 |
+
"jumped": 951,
|
1080 |
+
"glad": 952,
|
1081 |
+
"pet": 953,
|
1082 |
+
"##here": 954,
|
1083 |
+
"bit": 955,
|
1084 |
+
"per": 956,
|
1085 |
+
"##chen": 957,
|
1086 |
+
"kitchen": 958,
|
1087 |
+
"cra": 959,
|
1088 |
+
"helped": 960,
|
1089 |
+
"sees": 961,
|
1090 |
+
"dr": 962,
|
1091 |
+
"##outed": 963,
|
1092 |
+
"hear": 964,
|
1093 |
+
"sing": 965,
|
1094 |
+
"##ul": 966,
|
1095 |
+
"prin": 967,
|
1096 |
+
"happened": 968,
|
1097 |
+
"squ": 969,
|
1098 |
+
"yummy": 970,
|
1099 |
+
"grass": 971,
|
1100 |
+
"tri": 972,
|
1101 |
+
"ready": 973,
|
1102 |
+
"tommy": 974,
|
1103 |
+
"story": 975,
|
1104 |
+
"shouted": 976,
|
1105 |
+
"beh": 977,
|
1106 |
+
"##nts": 978,
|
1107 |
+
"really": 979,
|
1108 |
+
"brother": 980,
|
1109 |
+
"cr": 981,
|
1110 |
+
"reached": 982,
|
1111 |
+
"realized": 983,
|
1112 |
+
"lady": 984,
|
1113 |
+
"##ey": 985,
|
1114 |
+
"draw": 986,
|
1115 |
+
"having": 987,
|
1116 |
+
"##ins": 988,
|
1117 |
+
"through": 989,
|
1118 |
+
"favor": 990,
|
1119 |
+
"mess": 991,
|
1120 |
+
"cre": 992,
|
1121 |
+
"hat": 993,
|
1122 |
+
"favorite": 994,
|
1123 |
+
"game": 995,
|
1124 |
+
"less": 996,
|
1125 |
+
"ate": 997,
|
1126 |
+
"underst": 998,
|
1127 |
+
"soft": 999,
|
1128 |
+
"pare": 1000,
|
1129 |
+
"##zy": 1001,
|
1130 |
+
"thing": 1002,
|
1131 |
+
"##ket": 1003,
|
1132 |
+
"##ather": 1004,
|
1133 |
+
"##imes": 1005,
|
1134 |
+
"cu": 1006,
|
1135 |
+
"magic": 1007,
|
1136 |
+
"pretend": 1008,
|
1137 |
+
"began": 1009,
|
1138 |
+
"##where": 1010,
|
1139 |
+
"world": 1011,
|
1140 |
+
"looks": 1012,
|
1141 |
+
"##ken": 1013,
|
1142 |
+
"butterf": 1014,
|
1143 |
+
"himself": 1015,
|
1144 |
+
"kids": 1016,
|
1145 |
+
"##fully": 1017,
|
1146 |
+
"making": 1018,
|
1147 |
+
"done": 1019,
|
1148 |
+
"wow": 1020,
|
1149 |
+
"cut": 1021,
|
1150 |
+
"sometimes": 1022,
|
1151 |
+
"rest": 1023
|
1152 |
}
|
1153 |
}
|
1154 |
}
|
tokenizer_config.json
CHANGED
@@ -9,7 +9,7 @@
|
|
9 |
"special": true
|
10 |
},
|
11 |
"1": {
|
12 |
-
"content": "[
|
13 |
"lstrip": false,
|
14 |
"normalized": false,
|
15 |
"rstrip": false,
|
@@ -17,15 +17,7 @@
|
|
17 |
"special": true
|
18 |
},
|
19 |
"2": {
|
20 |
-
"content": "[
|
21 |
-
"lstrip": false,
|
22 |
-
"normalized": false,
|
23 |
-
"rstrip": false,
|
24 |
-
"single_word": false,
|
25 |
-
"special": true
|
26 |
-
},
|
27 |
-
"3": {
|
28 |
-
"content": "[PAD]",
|
29 |
"lstrip": false,
|
30 |
"normalized": false,
|
31 |
"rstrip": false,
|
|
|
9 |
"special": true
|
10 |
},
|
11 |
"1": {
|
12 |
+
"content": "[BOS]",
|
13 |
"lstrip": false,
|
14 |
"normalized": false,
|
15 |
"rstrip": false,
|
|
|
17 |
"special": true
|
18 |
},
|
19 |
"2": {
|
20 |
+
"content": "[EOS]",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
21 |
"lstrip": false,
|
22 |
"normalized": false,
|
23 |
"rstrip": false,
|