Update tokenizer_config.json from https://huggingface.co/Xenova/flan-t5-base/resolve/main/tokenizer_config.json
#1
by
rolf-mozilla
- opened
- tokenizer_config.json +0 -828
tokenizer_config.json
CHANGED
@@ -1,831 +1,4 @@
|
|
1 |
{
|
2 |
-
"add_prefix_space": true,
|
3 |
-
"added_tokens_decoder": {
|
4 |
-
"0": {
|
5 |
-
"content": "<pad>",
|
6 |
-
"lstrip": false,
|
7 |
-
"normalized": false,
|
8 |
-
"rstrip": false,
|
9 |
-
"single_word": false,
|
10 |
-
"special": true
|
11 |
-
},
|
12 |
-
"1": {
|
13 |
-
"content": "</s>",
|
14 |
-
"lstrip": false,
|
15 |
-
"normalized": false,
|
16 |
-
"rstrip": false,
|
17 |
-
"single_word": false,
|
18 |
-
"special": true
|
19 |
-
},
|
20 |
-
"2": {
|
21 |
-
"content": "<unk>",
|
22 |
-
"lstrip": false,
|
23 |
-
"normalized": false,
|
24 |
-
"rstrip": false,
|
25 |
-
"single_word": false,
|
26 |
-
"special": true
|
27 |
-
},
|
28 |
-
"32000": {
|
29 |
-
"content": "<extra_id_99>",
|
30 |
-
"lstrip": false,
|
31 |
-
"normalized": false,
|
32 |
-
"rstrip": false,
|
33 |
-
"single_word": false,
|
34 |
-
"special": true
|
35 |
-
},
|
36 |
-
"32001": {
|
37 |
-
"content": "<extra_id_98>",
|
38 |
-
"lstrip": false,
|
39 |
-
"normalized": false,
|
40 |
-
"rstrip": false,
|
41 |
-
"single_word": false,
|
42 |
-
"special": true
|
43 |
-
},
|
44 |
-
"32002": {
|
45 |
-
"content": "<extra_id_97>",
|
46 |
-
"lstrip": false,
|
47 |
-
"normalized": false,
|
48 |
-
"rstrip": false,
|
49 |
-
"single_word": false,
|
50 |
-
"special": true
|
51 |
-
},
|
52 |
-
"32003": {
|
53 |
-
"content": "<extra_id_96>",
|
54 |
-
"lstrip": false,
|
55 |
-
"normalized": false,
|
56 |
-
"rstrip": false,
|
57 |
-
"single_word": false,
|
58 |
-
"special": true
|
59 |
-
},
|
60 |
-
"32004": {
|
61 |
-
"content": "<extra_id_95>",
|
62 |
-
"lstrip": false,
|
63 |
-
"normalized": false,
|
64 |
-
"rstrip": false,
|
65 |
-
"single_word": false,
|
66 |
-
"special": true
|
67 |
-
},
|
68 |
-
"32005": {
|
69 |
-
"content": "<extra_id_94>",
|
70 |
-
"lstrip": false,
|
71 |
-
"normalized": false,
|
72 |
-
"rstrip": false,
|
73 |
-
"single_word": false,
|
74 |
-
"special": true
|
75 |
-
},
|
76 |
-
"32006": {
|
77 |
-
"content": "<extra_id_93>",
|
78 |
-
"lstrip": false,
|
79 |
-
"normalized": false,
|
80 |
-
"rstrip": false,
|
81 |
-
"single_word": false,
|
82 |
-
"special": true
|
83 |
-
},
|
84 |
-
"32007": {
|
85 |
-
"content": "<extra_id_92>",
|
86 |
-
"lstrip": false,
|
87 |
-
"normalized": false,
|
88 |
-
"rstrip": false,
|
89 |
-
"single_word": false,
|
90 |
-
"special": true
|
91 |
-
},
|
92 |
-
"32008": {
|
93 |
-
"content": "<extra_id_91>",
|
94 |
-
"lstrip": false,
|
95 |
-
"normalized": false,
|
96 |
-
"rstrip": false,
|
97 |
-
"single_word": false,
|
98 |
-
"special": true
|
99 |
-
},
|
100 |
-
"32009": {
|
101 |
-
"content": "<extra_id_90>",
|
102 |
-
"lstrip": false,
|
103 |
-
"normalized": false,
|
104 |
-
"rstrip": false,
|
105 |
-
"single_word": false,
|
106 |
-
"special": true
|
107 |
-
},
|
108 |
-
"32010": {
|
109 |
-
"content": "<extra_id_89>",
|
110 |
-
"lstrip": false,
|
111 |
-
"normalized": false,
|
112 |
-
"rstrip": false,
|
113 |
-
"single_word": false,
|
114 |
-
"special": true
|
115 |
-
},
|
116 |
-
"32011": {
|
117 |
-
"content": "<extra_id_88>",
|
118 |
-
"lstrip": false,
|
119 |
-
"normalized": false,
|
120 |
-
"rstrip": false,
|
121 |
-
"single_word": false,
|
122 |
-
"special": true
|
123 |
-
},
|
124 |
-
"32012": {
|
125 |
-
"content": "<extra_id_87>",
|
126 |
-
"lstrip": false,
|
127 |
-
"normalized": false,
|
128 |
-
"rstrip": false,
|
129 |
-
"single_word": false,
|
130 |
-
"special": true
|
131 |
-
},
|
132 |
-
"32013": {
|
133 |
-
"content": "<extra_id_86>",
|
134 |
-
"lstrip": false,
|
135 |
-
"normalized": false,
|
136 |
-
"rstrip": false,
|
137 |
-
"single_word": false,
|
138 |
-
"special": true
|
139 |
-
},
|
140 |
-
"32014": {
|
141 |
-
"content": "<extra_id_85>",
|
142 |
-
"lstrip": false,
|
143 |
-
"normalized": false,
|
144 |
-
"rstrip": false,
|
145 |
-
"single_word": false,
|
146 |
-
"special": true
|
147 |
-
},
|
148 |
-
"32015": {
|
149 |
-
"content": "<extra_id_84>",
|
150 |
-
"lstrip": false,
|
151 |
-
"normalized": false,
|
152 |
-
"rstrip": false,
|
153 |
-
"single_word": false,
|
154 |
-
"special": true
|
155 |
-
},
|
156 |
-
"32016": {
|
157 |
-
"content": "<extra_id_83>",
|
158 |
-
"lstrip": false,
|
159 |
-
"normalized": false,
|
160 |
-
"rstrip": false,
|
161 |
-
"single_word": false,
|
162 |
-
"special": true
|
163 |
-
},
|
164 |
-
"32017": {
|
165 |
-
"content": "<extra_id_82>",
|
166 |
-
"lstrip": false,
|
167 |
-
"normalized": false,
|
168 |
-
"rstrip": false,
|
169 |
-
"single_word": false,
|
170 |
-
"special": true
|
171 |
-
},
|
172 |
-
"32018": {
|
173 |
-
"content": "<extra_id_81>",
|
174 |
-
"lstrip": false,
|
175 |
-
"normalized": false,
|
176 |
-
"rstrip": false,
|
177 |
-
"single_word": false,
|
178 |
-
"special": true
|
179 |
-
},
|
180 |
-
"32019": {
|
181 |
-
"content": "<extra_id_80>",
|
182 |
-
"lstrip": false,
|
183 |
-
"normalized": false,
|
184 |
-
"rstrip": false,
|
185 |
-
"single_word": false,
|
186 |
-
"special": true
|
187 |
-
},
|
188 |
-
"32020": {
|
189 |
-
"content": "<extra_id_79>",
|
190 |
-
"lstrip": false,
|
191 |
-
"normalized": false,
|
192 |
-
"rstrip": false,
|
193 |
-
"single_word": false,
|
194 |
-
"special": true
|
195 |
-
},
|
196 |
-
"32021": {
|
197 |
-
"content": "<extra_id_78>",
|
198 |
-
"lstrip": false,
|
199 |
-
"normalized": false,
|
200 |
-
"rstrip": false,
|
201 |
-
"single_word": false,
|
202 |
-
"special": true
|
203 |
-
},
|
204 |
-
"32022": {
|
205 |
-
"content": "<extra_id_77>",
|
206 |
-
"lstrip": false,
|
207 |
-
"normalized": false,
|
208 |
-
"rstrip": false,
|
209 |
-
"single_word": false,
|
210 |
-
"special": true
|
211 |
-
},
|
212 |
-
"32023": {
|
213 |
-
"content": "<extra_id_76>",
|
214 |
-
"lstrip": false,
|
215 |
-
"normalized": false,
|
216 |
-
"rstrip": false,
|
217 |
-
"single_word": false,
|
218 |
-
"special": true
|
219 |
-
},
|
220 |
-
"32024": {
|
221 |
-
"content": "<extra_id_75>",
|
222 |
-
"lstrip": false,
|
223 |
-
"normalized": false,
|
224 |
-
"rstrip": false,
|
225 |
-
"single_word": false,
|
226 |
-
"special": true
|
227 |
-
},
|
228 |
-
"32025": {
|
229 |
-
"content": "<extra_id_74>",
|
230 |
-
"lstrip": false,
|
231 |
-
"normalized": false,
|
232 |
-
"rstrip": false,
|
233 |
-
"single_word": false,
|
234 |
-
"special": true
|
235 |
-
},
|
236 |
-
"32026": {
|
237 |
-
"content": "<extra_id_73>",
|
238 |
-
"lstrip": false,
|
239 |
-
"normalized": false,
|
240 |
-
"rstrip": false,
|
241 |
-
"single_word": false,
|
242 |
-
"special": true
|
243 |
-
},
|
244 |
-
"32027": {
|
245 |
-
"content": "<extra_id_72>",
|
246 |
-
"lstrip": false,
|
247 |
-
"normalized": false,
|
248 |
-
"rstrip": false,
|
249 |
-
"single_word": false,
|
250 |
-
"special": true
|
251 |
-
},
|
252 |
-
"32028": {
|
253 |
-
"content": "<extra_id_71>",
|
254 |
-
"lstrip": false,
|
255 |
-
"normalized": false,
|
256 |
-
"rstrip": false,
|
257 |
-
"single_word": false,
|
258 |
-
"special": true
|
259 |
-
},
|
260 |
-
"32029": {
|
261 |
-
"content": "<extra_id_70>",
|
262 |
-
"lstrip": false,
|
263 |
-
"normalized": false,
|
264 |
-
"rstrip": false,
|
265 |
-
"single_word": false,
|
266 |
-
"special": true
|
267 |
-
},
|
268 |
-
"32030": {
|
269 |
-
"content": "<extra_id_69>",
|
270 |
-
"lstrip": false,
|
271 |
-
"normalized": false,
|
272 |
-
"rstrip": false,
|
273 |
-
"single_word": false,
|
274 |
-
"special": true
|
275 |
-
},
|
276 |
-
"32031": {
|
277 |
-
"content": "<extra_id_68>",
|
278 |
-
"lstrip": false,
|
279 |
-
"normalized": false,
|
280 |
-
"rstrip": false,
|
281 |
-
"single_word": false,
|
282 |
-
"special": true
|
283 |
-
},
|
284 |
-
"32032": {
|
285 |
-
"content": "<extra_id_67>",
|
286 |
-
"lstrip": false,
|
287 |
-
"normalized": false,
|
288 |
-
"rstrip": false,
|
289 |
-
"single_word": false,
|
290 |
-
"special": true
|
291 |
-
},
|
292 |
-
"32033": {
|
293 |
-
"content": "<extra_id_66>",
|
294 |
-
"lstrip": false,
|
295 |
-
"normalized": false,
|
296 |
-
"rstrip": false,
|
297 |
-
"single_word": false,
|
298 |
-
"special": true
|
299 |
-
},
|
300 |
-
"32034": {
|
301 |
-
"content": "<extra_id_65>",
|
302 |
-
"lstrip": false,
|
303 |
-
"normalized": false,
|
304 |
-
"rstrip": false,
|
305 |
-
"single_word": false,
|
306 |
-
"special": true
|
307 |
-
},
|
308 |
-
"32035": {
|
309 |
-
"content": "<extra_id_64>",
|
310 |
-
"lstrip": false,
|
311 |
-
"normalized": false,
|
312 |
-
"rstrip": false,
|
313 |
-
"single_word": false,
|
314 |
-
"special": true
|
315 |
-
},
|
316 |
-
"32036": {
|
317 |
-
"content": "<extra_id_63>",
|
318 |
-
"lstrip": false,
|
319 |
-
"normalized": false,
|
320 |
-
"rstrip": false,
|
321 |
-
"single_word": false,
|
322 |
-
"special": true
|
323 |
-
},
|
324 |
-
"32037": {
|
325 |
-
"content": "<extra_id_62>",
|
326 |
-
"lstrip": false,
|
327 |
-
"normalized": false,
|
328 |
-
"rstrip": false,
|
329 |
-
"single_word": false,
|
330 |
-
"special": true
|
331 |
-
},
|
332 |
-
"32038": {
|
333 |
-
"content": "<extra_id_61>",
|
334 |
-
"lstrip": false,
|
335 |
-
"normalized": false,
|
336 |
-
"rstrip": false,
|
337 |
-
"single_word": false,
|
338 |
-
"special": true
|
339 |
-
},
|
340 |
-
"32039": {
|
341 |
-
"content": "<extra_id_60>",
|
342 |
-
"lstrip": false,
|
343 |
-
"normalized": false,
|
344 |
-
"rstrip": false,
|
345 |
-
"single_word": false,
|
346 |
-
"special": true
|
347 |
-
},
|
348 |
-
"32040": {
|
349 |
-
"content": "<extra_id_59>",
|
350 |
-
"lstrip": false,
|
351 |
-
"normalized": false,
|
352 |
-
"rstrip": false,
|
353 |
-
"single_word": false,
|
354 |
-
"special": true
|
355 |
-
},
|
356 |
-
"32041": {
|
357 |
-
"content": "<extra_id_58>",
|
358 |
-
"lstrip": false,
|
359 |
-
"normalized": false,
|
360 |
-
"rstrip": false,
|
361 |
-
"single_word": false,
|
362 |
-
"special": true
|
363 |
-
},
|
364 |
-
"32042": {
|
365 |
-
"content": "<extra_id_57>",
|
366 |
-
"lstrip": false,
|
367 |
-
"normalized": false,
|
368 |
-
"rstrip": false,
|
369 |
-
"single_word": false,
|
370 |
-
"special": true
|
371 |
-
},
|
372 |
-
"32043": {
|
373 |
-
"content": "<extra_id_56>",
|
374 |
-
"lstrip": false,
|
375 |
-
"normalized": false,
|
376 |
-
"rstrip": false,
|
377 |
-
"single_word": false,
|
378 |
-
"special": true
|
379 |
-
},
|
380 |
-
"32044": {
|
381 |
-
"content": "<extra_id_55>",
|
382 |
-
"lstrip": false,
|
383 |
-
"normalized": false,
|
384 |
-
"rstrip": false,
|
385 |
-
"single_word": false,
|
386 |
-
"special": true
|
387 |
-
},
|
388 |
-
"32045": {
|
389 |
-
"content": "<extra_id_54>",
|
390 |
-
"lstrip": false,
|
391 |
-
"normalized": false,
|
392 |
-
"rstrip": false,
|
393 |
-
"single_word": false,
|
394 |
-
"special": true
|
395 |
-
},
|
396 |
-
"32046": {
|
397 |
-
"content": "<extra_id_53>",
|
398 |
-
"lstrip": false,
|
399 |
-
"normalized": false,
|
400 |
-
"rstrip": false,
|
401 |
-
"single_word": false,
|
402 |
-
"special": true
|
403 |
-
},
|
404 |
-
"32047": {
|
405 |
-
"content": "<extra_id_52>",
|
406 |
-
"lstrip": false,
|
407 |
-
"normalized": false,
|
408 |
-
"rstrip": false,
|
409 |
-
"single_word": false,
|
410 |
-
"special": true
|
411 |
-
},
|
412 |
-
"32048": {
|
413 |
-
"content": "<extra_id_51>",
|
414 |
-
"lstrip": false,
|
415 |
-
"normalized": false,
|
416 |
-
"rstrip": false,
|
417 |
-
"single_word": false,
|
418 |
-
"special": true
|
419 |
-
},
|
420 |
-
"32049": {
|
421 |
-
"content": "<extra_id_50>",
|
422 |
-
"lstrip": false,
|
423 |
-
"normalized": false,
|
424 |
-
"rstrip": false,
|
425 |
-
"single_word": false,
|
426 |
-
"special": true
|
427 |
-
},
|
428 |
-
"32050": {
|
429 |
-
"content": "<extra_id_49>",
|
430 |
-
"lstrip": false,
|
431 |
-
"normalized": false,
|
432 |
-
"rstrip": false,
|
433 |
-
"single_word": false,
|
434 |
-
"special": true
|
435 |
-
},
|
436 |
-
"32051": {
|
437 |
-
"content": "<extra_id_48>",
|
438 |
-
"lstrip": false,
|
439 |
-
"normalized": false,
|
440 |
-
"rstrip": false,
|
441 |
-
"single_word": false,
|
442 |
-
"special": true
|
443 |
-
},
|
444 |
-
"32052": {
|
445 |
-
"content": "<extra_id_47>",
|
446 |
-
"lstrip": false,
|
447 |
-
"normalized": false,
|
448 |
-
"rstrip": false,
|
449 |
-
"single_word": false,
|
450 |
-
"special": true
|
451 |
-
},
|
452 |
-
"32053": {
|
453 |
-
"content": "<extra_id_46>",
|
454 |
-
"lstrip": false,
|
455 |
-
"normalized": false,
|
456 |
-
"rstrip": false,
|
457 |
-
"single_word": false,
|
458 |
-
"special": true
|
459 |
-
},
|
460 |
-
"32054": {
|
461 |
-
"content": "<extra_id_45>",
|
462 |
-
"lstrip": false,
|
463 |
-
"normalized": false,
|
464 |
-
"rstrip": false,
|
465 |
-
"single_word": false,
|
466 |
-
"special": true
|
467 |
-
},
|
468 |
-
"32055": {
|
469 |
-
"content": "<extra_id_44>",
|
470 |
-
"lstrip": false,
|
471 |
-
"normalized": false,
|
472 |
-
"rstrip": false,
|
473 |
-
"single_word": false,
|
474 |
-
"special": true
|
475 |
-
},
|
476 |
-
"32056": {
|
477 |
-
"content": "<extra_id_43>",
|
478 |
-
"lstrip": false,
|
479 |
-
"normalized": false,
|
480 |
-
"rstrip": false,
|
481 |
-
"single_word": false,
|
482 |
-
"special": true
|
483 |
-
},
|
484 |
-
"32057": {
|
485 |
-
"content": "<extra_id_42>",
|
486 |
-
"lstrip": false,
|
487 |
-
"normalized": false,
|
488 |
-
"rstrip": false,
|
489 |
-
"single_word": false,
|
490 |
-
"special": true
|
491 |
-
},
|
492 |
-
"32058": {
|
493 |
-
"content": "<extra_id_41>",
|
494 |
-
"lstrip": false,
|
495 |
-
"normalized": false,
|
496 |
-
"rstrip": false,
|
497 |
-
"single_word": false,
|
498 |
-
"special": true
|
499 |
-
},
|
500 |
-
"32059": {
|
501 |
-
"content": "<extra_id_40>",
|
502 |
-
"lstrip": false,
|
503 |
-
"normalized": false,
|
504 |
-
"rstrip": false,
|
505 |
-
"single_word": false,
|
506 |
-
"special": true
|
507 |
-
},
|
508 |
-
"32060": {
|
509 |
-
"content": "<extra_id_39>",
|
510 |
-
"lstrip": false,
|
511 |
-
"normalized": false,
|
512 |
-
"rstrip": false,
|
513 |
-
"single_word": false,
|
514 |
-
"special": true
|
515 |
-
},
|
516 |
-
"32061": {
|
517 |
-
"content": "<extra_id_38>",
|
518 |
-
"lstrip": false,
|
519 |
-
"normalized": false,
|
520 |
-
"rstrip": false,
|
521 |
-
"single_word": false,
|
522 |
-
"special": true
|
523 |
-
},
|
524 |
-
"32062": {
|
525 |
-
"content": "<extra_id_37>",
|
526 |
-
"lstrip": false,
|
527 |
-
"normalized": false,
|
528 |
-
"rstrip": false,
|
529 |
-
"single_word": false,
|
530 |
-
"special": true
|
531 |
-
},
|
532 |
-
"32063": {
|
533 |
-
"content": "<extra_id_36>",
|
534 |
-
"lstrip": false,
|
535 |
-
"normalized": false,
|
536 |
-
"rstrip": false,
|
537 |
-
"single_word": false,
|
538 |
-
"special": true
|
539 |
-
},
|
540 |
-
"32064": {
|
541 |
-
"content": "<extra_id_35>",
|
542 |
-
"lstrip": false,
|
543 |
-
"normalized": false,
|
544 |
-
"rstrip": false,
|
545 |
-
"single_word": false,
|
546 |
-
"special": true
|
547 |
-
},
|
548 |
-
"32065": {
|
549 |
-
"content": "<extra_id_34>",
|
550 |
-
"lstrip": false,
|
551 |
-
"normalized": false,
|
552 |
-
"rstrip": false,
|
553 |
-
"single_word": false,
|
554 |
-
"special": true
|
555 |
-
},
|
556 |
-
"32066": {
|
557 |
-
"content": "<extra_id_33>",
|
558 |
-
"lstrip": false,
|
559 |
-
"normalized": false,
|
560 |
-
"rstrip": false,
|
561 |
-
"single_word": false,
|
562 |
-
"special": true
|
563 |
-
},
|
564 |
-
"32067": {
|
565 |
-
"content": "<extra_id_32>",
|
566 |
-
"lstrip": false,
|
567 |
-
"normalized": false,
|
568 |
-
"rstrip": false,
|
569 |
-
"single_word": false,
|
570 |
-
"special": true
|
571 |
-
},
|
572 |
-
"32068": {
|
573 |
-
"content": "<extra_id_31>",
|
574 |
-
"lstrip": false,
|
575 |
-
"normalized": false,
|
576 |
-
"rstrip": false,
|
577 |
-
"single_word": false,
|
578 |
-
"special": true
|
579 |
-
},
|
580 |
-
"32069": {
|
581 |
-
"content": "<extra_id_30>",
|
582 |
-
"lstrip": false,
|
583 |
-
"normalized": false,
|
584 |
-
"rstrip": false,
|
585 |
-
"single_word": false,
|
586 |
-
"special": true
|
587 |
-
},
|
588 |
-
"32070": {
|
589 |
-
"content": "<extra_id_29>",
|
590 |
-
"lstrip": false,
|
591 |
-
"normalized": false,
|
592 |
-
"rstrip": false,
|
593 |
-
"single_word": false,
|
594 |
-
"special": true
|
595 |
-
},
|
596 |
-
"32071": {
|
597 |
-
"content": "<extra_id_28>",
|
598 |
-
"lstrip": false,
|
599 |
-
"normalized": false,
|
600 |
-
"rstrip": false,
|
601 |
-
"single_word": false,
|
602 |
-
"special": true
|
603 |
-
},
|
604 |
-
"32072": {
|
605 |
-
"content": "<extra_id_27>",
|
606 |
-
"lstrip": false,
|
607 |
-
"normalized": false,
|
608 |
-
"rstrip": false,
|
609 |
-
"single_word": false,
|
610 |
-
"special": true
|
611 |
-
},
|
612 |
-
"32073": {
|
613 |
-
"content": "<extra_id_26>",
|
614 |
-
"lstrip": false,
|
615 |
-
"normalized": false,
|
616 |
-
"rstrip": false,
|
617 |
-
"single_word": false,
|
618 |
-
"special": true
|
619 |
-
},
|
620 |
-
"32074": {
|
621 |
-
"content": "<extra_id_25>",
|
622 |
-
"lstrip": false,
|
623 |
-
"normalized": false,
|
624 |
-
"rstrip": false,
|
625 |
-
"single_word": false,
|
626 |
-
"special": true
|
627 |
-
},
|
628 |
-
"32075": {
|
629 |
-
"content": "<extra_id_24>",
|
630 |
-
"lstrip": false,
|
631 |
-
"normalized": false,
|
632 |
-
"rstrip": false,
|
633 |
-
"single_word": false,
|
634 |
-
"special": true
|
635 |
-
},
|
636 |
-
"32076": {
|
637 |
-
"content": "<extra_id_23>",
|
638 |
-
"lstrip": false,
|
639 |
-
"normalized": false,
|
640 |
-
"rstrip": false,
|
641 |
-
"single_word": false,
|
642 |
-
"special": true
|
643 |
-
},
|
644 |
-
"32077": {
|
645 |
-
"content": "<extra_id_22>",
|
646 |
-
"lstrip": false,
|
647 |
-
"normalized": false,
|
648 |
-
"rstrip": false,
|
649 |
-
"single_word": false,
|
650 |
-
"special": true
|
651 |
-
},
|
652 |
-
"32078": {
|
653 |
-
"content": "<extra_id_21>",
|
654 |
-
"lstrip": false,
|
655 |
-
"normalized": false,
|
656 |
-
"rstrip": false,
|
657 |
-
"single_word": false,
|
658 |
-
"special": true
|
659 |
-
},
|
660 |
-
"32079": {
|
661 |
-
"content": "<extra_id_20>",
|
662 |
-
"lstrip": false,
|
663 |
-
"normalized": false,
|
664 |
-
"rstrip": false,
|
665 |
-
"single_word": false,
|
666 |
-
"special": true
|
667 |
-
},
|
668 |
-
"32080": {
|
669 |
-
"content": "<extra_id_19>",
|
670 |
-
"lstrip": false,
|
671 |
-
"normalized": false,
|
672 |
-
"rstrip": false,
|
673 |
-
"single_word": false,
|
674 |
-
"special": true
|
675 |
-
},
|
676 |
-
"32081": {
|
677 |
-
"content": "<extra_id_18>",
|
678 |
-
"lstrip": false,
|
679 |
-
"normalized": false,
|
680 |
-
"rstrip": false,
|
681 |
-
"single_word": false,
|
682 |
-
"special": true
|
683 |
-
},
|
684 |
-
"32082": {
|
685 |
-
"content": "<extra_id_17>",
|
686 |
-
"lstrip": false,
|
687 |
-
"normalized": false,
|
688 |
-
"rstrip": false,
|
689 |
-
"single_word": false,
|
690 |
-
"special": true
|
691 |
-
},
|
692 |
-
"32083": {
|
693 |
-
"content": "<extra_id_16>",
|
694 |
-
"lstrip": false,
|
695 |
-
"normalized": false,
|
696 |
-
"rstrip": false,
|
697 |
-
"single_word": false,
|
698 |
-
"special": true
|
699 |
-
},
|
700 |
-
"32084": {
|
701 |
-
"content": "<extra_id_15>",
|
702 |
-
"lstrip": false,
|
703 |
-
"normalized": false,
|
704 |
-
"rstrip": false,
|
705 |
-
"single_word": false,
|
706 |
-
"special": true
|
707 |
-
},
|
708 |
-
"32085": {
|
709 |
-
"content": "<extra_id_14>",
|
710 |
-
"lstrip": false,
|
711 |
-
"normalized": false,
|
712 |
-
"rstrip": false,
|
713 |
-
"single_word": false,
|
714 |
-
"special": true
|
715 |
-
},
|
716 |
-
"32086": {
|
717 |
-
"content": "<extra_id_13>",
|
718 |
-
"lstrip": false,
|
719 |
-
"normalized": false,
|
720 |
-
"rstrip": false,
|
721 |
-
"single_word": false,
|
722 |
-
"special": true
|
723 |
-
},
|
724 |
-
"32087": {
|
725 |
-
"content": "<extra_id_12>",
|
726 |
-
"lstrip": false,
|
727 |
-
"normalized": false,
|
728 |
-
"rstrip": false,
|
729 |
-
"single_word": false,
|
730 |
-
"special": true
|
731 |
-
},
|
732 |
-
"32088": {
|
733 |
-
"content": "<extra_id_11>",
|
734 |
-
"lstrip": false,
|
735 |
-
"normalized": false,
|
736 |
-
"rstrip": false,
|
737 |
-
"single_word": false,
|
738 |
-
"special": true
|
739 |
-
},
|
740 |
-
"32089": {
|
741 |
-
"content": "<extra_id_10>",
|
742 |
-
"lstrip": false,
|
743 |
-
"normalized": false,
|
744 |
-
"rstrip": false,
|
745 |
-
"single_word": false,
|
746 |
-
"special": true
|
747 |
-
},
|
748 |
-
"32090": {
|
749 |
-
"content": "<extra_id_9>",
|
750 |
-
"lstrip": false,
|
751 |
-
"normalized": false,
|
752 |
-
"rstrip": false,
|
753 |
-
"single_word": false,
|
754 |
-
"special": true
|
755 |
-
},
|
756 |
-
"32091": {
|
757 |
-
"content": "<extra_id_8>",
|
758 |
-
"lstrip": false,
|
759 |
-
"normalized": false,
|
760 |
-
"rstrip": false,
|
761 |
-
"single_word": false,
|
762 |
-
"special": true
|
763 |
-
},
|
764 |
-
"32092": {
|
765 |
-
"content": "<extra_id_7>",
|
766 |
-
"lstrip": false,
|
767 |
-
"normalized": false,
|
768 |
-
"rstrip": false,
|
769 |
-
"single_word": false,
|
770 |
-
"special": true
|
771 |
-
},
|
772 |
-
"32093": {
|
773 |
-
"content": "<extra_id_6>",
|
774 |
-
"lstrip": false,
|
775 |
-
"normalized": false,
|
776 |
-
"rstrip": false,
|
777 |
-
"single_word": false,
|
778 |
-
"special": true
|
779 |
-
},
|
780 |
-
"32094": {
|
781 |
-
"content": "<extra_id_5>",
|
782 |
-
"lstrip": false,
|
783 |
-
"normalized": false,
|
784 |
-
"rstrip": false,
|
785 |
-
"single_word": false,
|
786 |
-
"special": true
|
787 |
-
},
|
788 |
-
"32095": {
|
789 |
-
"content": "<extra_id_4>",
|
790 |
-
"lstrip": false,
|
791 |
-
"normalized": false,
|
792 |
-
"rstrip": false,
|
793 |
-
"single_word": false,
|
794 |
-
"special": true
|
795 |
-
},
|
796 |
-
"32096": {
|
797 |
-
"content": "<extra_id_3>",
|
798 |
-
"lstrip": false,
|
799 |
-
"normalized": false,
|
800 |
-
"rstrip": false,
|
801 |
-
"single_word": false,
|
802 |
-
"special": true
|
803 |
-
},
|
804 |
-
"32097": {
|
805 |
-
"content": "<extra_id_2>",
|
806 |
-
"lstrip": false,
|
807 |
-
"normalized": false,
|
808 |
-
"rstrip": false,
|
809 |
-
"single_word": false,
|
810 |
-
"special": true
|
811 |
-
},
|
812 |
-
"32098": {
|
813 |
-
"content": "<extra_id_1>",
|
814 |
-
"lstrip": false,
|
815 |
-
"normalized": false,
|
816 |
-
"rstrip": false,
|
817 |
-
"single_word": false,
|
818 |
-
"special": true
|
819 |
-
},
|
820 |
-
"32099": {
|
821 |
-
"content": "<extra_id_0>",
|
822 |
-
"lstrip": false,
|
823 |
-
"normalized": false,
|
824 |
-
"rstrip": false,
|
825 |
-
"single_word": false,
|
826 |
-
"special": true
|
827 |
-
}
|
828 |
-
},
|
829 |
"additional_special_tokens": [
|
830 |
"<extra_id_0>",
|
831 |
"<extra_id_1>",
|
@@ -931,7 +104,6 @@
|
|
931 |
"clean_up_tokenization_spaces": true,
|
932 |
"eos_token": "</s>",
|
933 |
"extra_ids": 100,
|
934 |
-
"legacy": true,
|
935 |
"model_max_length": 512,
|
936 |
"pad_token": "<pad>",
|
937 |
"sp_model_kwargs": {},
|
|
|
1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2 |
"additional_special_tokens": [
|
3 |
"<extra_id_0>",
|
4 |
"<extra_id_1>",
|
|
|
104 |
"clean_up_tokenization_spaces": true,
|
105 |
"eos_token": "</s>",
|
106 |
"extra_ids": 100,
|
|
|
107 |
"model_max_length": 512,
|
108 |
"pad_token": "<pad>",
|
109 |
"sp_model_kwargs": {},
|