Remove file information section (#3)
Browse files- Remove file information section (b449a163fde32b00cf17346d73a3fac28ed50761)
Co-authored-by: Niels Rogge <[email protected]>
README.md
CHANGED
@@ -86,802 +86,4 @@ All of our results, traces from experiments are located in `ablation_results/`
|
|
86 |
|
87 |
Note: Our predictor design has improved since the arXiv paper release (We added a layer-norm to stabilize training). Further, to focus on the main predictor design and training-eval scripts, we have removed the ablation scripts. To reproduce the original results and predictor models, please checkout commit `0412fc24a3b770e4d82e6d7064a8172f24c5fcd3` and download the old models from [Drive Link](https://drive.google.com/drive/folders/1psNZ1SU0LaZJ-x5MQGH59CzYSmeT4yRf?usp=sharing).
|
88 |
|
89 |
-
For the latest, new models, try the huggingface integration. [Wandb-Logs](https://wandb.ai/akhauriyash/TrainTokenButler) for trained models.
|
90 |
-
|
91 |
-
# File information
|
92 |
-
|
93 |
-
The repository contains the following file information:
|
94 |
-
|
95 |
-
Filename: tokenizer.json
|
96 |
-
Content: "Content of the file is larger than 50 KB, too long to display."
|
97 |
-
|
98 |
-
Filename: pytorch_model.bin.index.json
|
99 |
-
Content: "Content of the file is larger than 50 KB, too long to display."
|
100 |
-
|
101 |
-
Filename: generation_config.json
|
102 |
-
Content: {
|
103 |
-
"_from_model_config": true,
|
104 |
-
"bos_token_id": 128000,
|
105 |
-
"eos_token_id": 128001,
|
106 |
-
"transformers_version": "4.48.3"
|
107 |
-
}
|
108 |
-
|
109 |
-
Filename: special_tokens_map.json
|
110 |
-
Content: {
|
111 |
-
"bos_token": {
|
112 |
-
"content": "<|begin_of_text|>",
|
113 |
-
"lstrip": false,
|
114 |
-
"normalized": false,
|
115 |
-
"rstrip": false,
|
116 |
-
"single_word": false
|
117 |
-
},
|
118 |
-
"eos_token": {
|
119 |
-
"content": "<|end_of_text|>",
|
120 |
-
"lstrip": false,
|
121 |
-
"normalized": false,
|
122 |
-
"rstrip": false,
|
123 |
-
"single_word": false
|
124 |
-
}
|
125 |
-
}
|
126 |
-
|
127 |
-
Filename: tokenizer_config.json
|
128 |
-
Content: {
|
129 |
-
"added_tokens_decoder": {
|
130 |
-
"128000": {
|
131 |
-
"content": "<|begin_of_text|>",
|
132 |
-
"lstrip": false,
|
133 |
-
"normalized": false,
|
134 |
-
"rstrip": false,
|
135 |
-
"single_word": false,
|
136 |
-
"special": true
|
137 |
-
},
|
138 |
-
"128001": {
|
139 |
-
"content": "<|end_of_text|>",
|
140 |
-
"lstrip": false,
|
141 |
-
"normalized": false,
|
142 |
-
"rstrip": false,
|
143 |
-
"single_word": false,
|
144 |
-
"special": true
|
145 |
-
},
|
146 |
-
"128002": {
|
147 |
-
"content": "<|reserved_special_token_0|>",
|
148 |
-
"lstrip": false,
|
149 |
-
"normalized": false,
|
150 |
-
"rstrip": false,
|
151 |
-
"single_word": false,
|
152 |
-
"special": true
|
153 |
-
},
|
154 |
-
"128003": {
|
155 |
-
"content": "<|reserved_special_token_1|>",
|
156 |
-
"lstrip": false,
|
157 |
-
"normalized": false,
|
158 |
-
"rstrip": false,
|
159 |
-
"single_word": false,
|
160 |
-
"special": true
|
161 |
-
},
|
162 |
-
"128004": {
|
163 |
-
"content": "<|finetune_right_pad_id|>",
|
164 |
-
"lstrip": false,
|
165 |
-
"normalized": false,
|
166 |
-
"rstrip": false,
|
167 |
-
"single_word": false,
|
168 |
-
"special": true
|
169 |
-
},
|
170 |
-
"128005": {
|
171 |
-
"content": "<|reserved_special_token_2|>",
|
172 |
-
"lstrip": false,
|
173 |
-
"normalized": false,
|
174 |
-
"rstrip": false,
|
175 |
-
"single_word": false,
|
176 |
-
"special": true
|
177 |
-
},
|
178 |
-
"128006": {
|
179 |
-
"content": "<|start_header_id|>",
|
180 |
-
"lstrip": false,
|
181 |
-
"normalized": false,
|
182 |
-
"rstrip": false,
|
183 |
-
"single_word": false,
|
184 |
-
"special": true
|
185 |
-
},
|
186 |
-
"128007": {
|
187 |
-
"content": "<|end_header_id|>",
|
188 |
-
"lstrip": false,
|
189 |
-
"normalized": false,
|
190 |
-
"rstrip": false,
|
191 |
-
"single_word": false,
|
192 |
-
"special": true
|
193 |
-
},
|
194 |
-
"128008": {
|
195 |
-
"content": "<|eom_id|>",
|
196 |
-
"lstrip": false,
|
197 |
-
"normalized": false,
|
198 |
-
"rstrip": false,
|
199 |
-
"single_word": false,
|
200 |
-
"special": true
|
201 |
-
},
|
202 |
-
"128009": {
|
203 |
-
"content": "<|eot_id|>",
|
204 |
-
"lstrip": false,
|
205 |
-
"normalized": false,
|
206 |
-
"rstrip": false,
|
207 |
-
"single_word": false,
|
208 |
-
"special": true
|
209 |
-
},
|
210 |
-
"128010": {
|
211 |
-
"content": "<|python_tag|>",
|
212 |
-
"lstrip": false,
|
213 |
-
"normalized": false,
|
214 |
-
"rstrip": false,
|
215 |
-
"single_word": false,
|
216 |
-
"special": true
|
217 |
-
},
|
218 |
-
"128011": {
|
219 |
-
"content": "<|reserved_special_token_3|>",
|
220 |
-
"lstrip": false,
|
221 |
-
"normalized": false,
|
222 |
-
"rstrip": false,
|
223 |
-
"single_word": false,
|
224 |
-
"special": true
|
225 |
-
},
|
226 |
-
"128012": {
|
227 |
-
"content": "<|reserved_special_token_4|>",
|
228 |
-
"lstrip": false,
|
229 |
-
"normalized": false,
|
230 |
-
"rstrip": false,
|
231 |
-
"single_word": false,
|
232 |
-
"special": true
|
233 |
-
},
|
234 |
-
"128013": {
|
235 |
-
"content": "<|reserved_special_token_5|>",
|
236 |
-
"lstrip": false,
|
237 |
-
"normalized": false,
|
238 |
-
"rstrip": false,
|
239 |
-
"single_word": false,
|
240 |
-
"special": true
|
241 |
-
},
|
242 |
-
"128014": {
|
243 |
-
"content": "<|reserved_special_token_6|>",
|
244 |
-
"lstrip": false,
|
245 |
-
"normalized": false,
|
246 |
-
"rstrip": false,
|
247 |
-
"single_word": false,
|
248 |
-
"special": true
|
249 |
-
},
|
250 |
-
"128015": {
|
251 |
-
"content": "<|reserved_special_token_7|>",
|
252 |
-
"lstrip": false,
|
253 |
-
"normalized": false,
|
254 |
-
"rstrip": false,
|
255 |
-
"single_word": false,
|
256 |
-
"special": true
|
257 |
-
},
|
258 |
-
"128016": {
|
259 |
-
"content": "<|reserved_special_token_8|>",
|
260 |
-
"lstrip": false,
|
261 |
-
"normalized": false,
|
262 |
-
"rstrip": false,
|
263 |
-
"single_word": false,
|
264 |
-
"special": true
|
265 |
-
},
|
266 |
-
"128017": {
|
267 |
-
"content": "<|reserved_special_token_9|>",
|
268 |
-
"lstrip": false,
|
269 |
-
"normalized": false,
|
270 |
-
"rstrip": false,
|
271 |
-
"single_word": false,
|
272 |
-
"special": true
|
273 |
-
},
|
274 |
-
"128018": {
|
275 |
-
"content": "<|reserved_special_token_10|>",
|
276 |
-
"lstrip": false,
|
277 |
-
"normalized": false,
|
278 |
-
"rstrip": false,
|
279 |
-
"single_word": false,
|
280 |
-
"special": true
|
281 |
-
},
|
282 |
-
"128019": {
|
283 |
-
"content": "<|reserved_special_token_11|>",
|
284 |
-
"lstrip": false,
|
285 |
-
"normalized": false,
|
286 |
-
"rstrip": false,
|
287 |
-
"single_word": false,
|
288 |
-
"special": true
|
289 |
-
},
|
290 |
-
"128020": {
|
291 |
-
"content": "<|reserved_special_token_12|>",
|
292 |
-
"lstrip": false,
|
293 |
-
"normalized": false,
|
294 |
-
"rstrip": false,
|
295 |
-
"single_word": false,
|
296 |
-
"special": true
|
297 |
-
},
|
298 |
-
"128021": {
|
299 |
-
"content": "<|reserved_special_token_13|>",
|
300 |
-
"lstrip": false,
|
301 |
-
"normalized": false,
|
302 |
-
"rstrip": false,
|
303 |
-
"single_word": false,
|
304 |
-
"special": true
|
305 |
-
},
|
306 |
-
"128022": {
|
307 |
-
"content": "<|reserved_special_token_14|>",
|
308 |
-
"lstrip": false,
|
309 |
-
"normalized": false,
|
310 |
-
"rstrip": false,
|
311 |
-
"single_word": false,
|
312 |
-
"special": true
|
313 |
-
},
|
314 |
-
"128023": {
|
315 |
-
"content": "<|reserved_special_token_15|>",
|
316 |
-
"lstrip": false,
|
317 |
-
"normalized": false,
|
318 |
-
"rstrip": false,
|
319 |
-
"single_word": false,
|
320 |
-
"special": true
|
321 |
-
},
|
322 |
-
"128024": {
|
323 |
-
"content": "<|reserved_special_token_16|>",
|
324 |
-
"lstrip": false,
|
325 |
-
"normalized": false,
|
326 |
-
"rstrip": false,
|
327 |
-
"single_word": false,
|
328 |
-
"special": true
|
329 |
-
},
|
330 |
-
"128025": {
|
331 |
-
"content": "<|reserved_special_token_17|>",
|
332 |
-
"lstrip": false,
|
333 |
-
"normalized": false,
|
334 |
-
"rstrip": false,
|
335 |
-
"single_word": false,
|
336 |
-
"special": true
|
337 |
-
},
|
338 |
-
"128026": {
|
339 |
-
"content": "<|reserved_special_token_18|>",
|
340 |
-
"lstrip": false,
|
341 |
-
"normalized": false,
|
342 |
-
"rstrip": false,
|
343 |
-
"single_word": false,
|
344 |
-
"special": true
|
345 |
-
},
|
346 |
-
"128027": {
|
347 |
-
"content": "<|reserved_special_token_19|>",
|
348 |
-
"lstrip": false,
|
349 |
-
"normalized": false,
|
350 |
-
"rstrip": false,
|
351 |
-
"single_word": false,
|
352 |
-
"special": true
|
353 |
-
},
|
354 |
-
"128028": {
|
355 |
-
"content": "<|reserved_special_token_20|>",
|
356 |
-
"lstrip": false,
|
357 |
-
"normalized": false,
|
358 |
-
"rstrip": false,
|
359 |
-
"single_word": false,
|
360 |
-
"special": true
|
361 |
-
},
|
362 |
-
"128029": {
|
363 |
-
"content": "<|reserved_special_token_21|>",
|
364 |
-
"lstrip": false,
|
365 |
-
"normalized": false,
|
366 |
-
"rstrip": false,
|
367 |
-
"single_word": false,
|
368 |
-
"special": true
|
369 |
-
},
|
370 |
-
"128030": {
|
371 |
-
"content": "<|reserved_special_token_22|>",
|
372 |
-
"lstrip": false,
|
373 |
-
"normalized": false,
|
374 |
-
"rstrip": false,
|
375 |
-
"single_word": false,
|
376 |
-
"special": true
|
377 |
-
},
|
378 |
-
"128031": {
|
379 |
-
"content": "<|reserved_special_token_23|>",
|
380 |
-
"lstrip": false,
|
381 |
-
"normalized": false,
|
382 |
-
"rstrip": false,
|
383 |
-
"single_word": false,
|
384 |
-
"special": true
|
385 |
-
},
|
386 |
-
"128032": {
|
387 |
-
"content": "<|reserved_special_token_24|>",
|
388 |
-
"lstrip": false,
|
389 |
-
"normalized": false,
|
390 |
-
"rstrip": false,
|
391 |
-
"single_word": false,
|
392 |
-
"special": true
|
393 |
-
},
|
394 |
-
"128033": {
|
395 |
-
"content": "<|reserved_special_token_25|>",
|
396 |
-
"lstrip": false,
|
397 |
-
"normalized": false,
|
398 |
-
"rstrip": false,
|
399 |
-
"single_word": false,
|
400 |
-
"special": true
|
401 |
-
},
|
402 |
-
"128034": {
|
403 |
-
"content": "<|reserved_special_token_26|>",
|
404 |
-
"lstrip": false,
|
405 |
-
"normalized": false,
|
406 |
-
"rstrip": false,
|
407 |
-
"single_word": false,
|
408 |
-
"special": true
|
409 |
-
},
|
410 |
-
"128035": {
|
411 |
-
"content": "<|reserved_special_token_27|>",
|
412 |
-
"lstrip": false,
|
413 |
-
"normalized": false,
|
414 |
-
"rstrip": false,
|
415 |
-
"single_word": false,
|
416 |
-
"special": true
|
417 |
-
},
|
418 |
-
"128036": {
|
419 |
-
"content": "<|reserved_special_token_28|>",
|
420 |
-
"lstrip": false,
|
421 |
-
"normalized": false,
|
422 |
-
"rstrip": false,
|
423 |
-
"single_word": false,
|
424 |
-
"special": true
|
425 |
-
},
|
426 |
-
"128037": {
|
427 |
-
"content": "<|reserved_special_token_29|>",
|
428 |
-
"lstrip": false,
|
429 |
-
"normalized": false,
|
430 |
-
"rstrip": false,
|
431 |
-
"single_word": false,
|
432 |
-
"special": true
|
433 |
-
},
|
434 |
-
"128038": {
|
435 |
-
"content": "<|reserved_special_token_30|>",
|
436 |
-
"lstrip": false,
|
437 |
-
"normalized": false,
|
438 |
-
"rstrip": false,
|
439 |
-
"single_word": false,
|
440 |
-
"special": true
|
441 |
-
},
|
442 |
-
"128039": {
|
443 |
-
"content": "<|reserved_special_token_31|>",
|
444 |
-
"lstrip": false,
|
445 |
-
"normalized": false,
|
446 |
-
"rstrip": false,
|
447 |
-
"single_word": false,
|
448 |
-
"special": true
|
449 |
-
},
|
450 |
-
"128040": {
|
451 |
-
"content": "<|reserved_special_token_32|>",
|
452 |
-
"lstrip": false,
|
453 |
-
"normalized": false,
|
454 |
-
"rstrip": false,
|
455 |
-
"single_word": false,
|
456 |
-
"special": true
|
457 |
-
},
|
458 |
-
"128041": {
|
459 |
-
"content": "<|reserved_special_token_33|>",
|
460 |
-
"lstrip": false,
|
461 |
-
"normalized": false,
|
462 |
-
"rstrip": false,
|
463 |
-
"single_word": false,
|
464 |
-
"special": true
|
465 |
-
},
|
466 |
-
"128042": {
|
467 |
-
"content": "<|reserved_special_token_34|>",
|
468 |
-
"lstrip": false,
|
469 |
-
"normalized": false,
|
470 |
-
"rstrip": false,
|
471 |
-
"single_word": false,
|
472 |
-
"special": true
|
473 |
-
},
|
474 |
-
"128043": {
|
475 |
-
"content": "<|reserved_special_token_35|>",
|
476 |
-
"lstrip": false,
|
477 |
-
"normalized": false,
|
478 |
-
"rstrip": false,
|
479 |
-
"single_word": false,
|
480 |
-
"special": true
|
481 |
-
},
|
482 |
-
"128044": {
|
483 |
-
"content": "<|reserved_special_token_36|>",
|
484 |
-
"lstrip": false,
|
485 |
-
"normalized": false,
|
486 |
-
"rstrip": false,
|
487 |
-
"single_word": false,
|
488 |
-
"special": true
|
489 |
-
},
|
490 |
-
"128045": {
|
491 |
-
"content": "<|reserved_special_token_37|>",
|
492 |
-
"lstrip": false,
|
493 |
-
"normalized": false,
|
494 |
-
"rstrip": false,
|
495 |
-
"single_word": false,
|
496 |
-
"special": true
|
497 |
-
},
|
498 |
-
"128046": {
|
499 |
-
"content": "<|reserved_special_token_38|>",
|
500 |
-
"lstrip": false,
|
501 |
-
"normalized": false,
|
502 |
-
"rstrip": false,
|
503 |
-
"single_word": false,
|
504 |
-
"special": true
|
505 |
-
},
|
506 |
-
"128047": {
|
507 |
-
"content": "<|reserved_special_token_39|>",
|
508 |
-
"lstrip": false,
|
509 |
-
"normalized": false,
|
510 |
-
"rstrip": false,
|
511 |
-
"single_word": false,
|
512 |
-
"special": true
|
513 |
-
},
|
514 |
-
"128048": {
|
515 |
-
"content": "<|reserved_special_token_40|>",
|
516 |
-
"lstrip": false,
|
517 |
-
"normalized": false,
|
518 |
-
"rstrip": false,
|
519 |
-
"single_word": false,
|
520 |
-
"special": true
|
521 |
-
},
|
522 |
-
"128049": {
|
523 |
-
"content": "<|reserved_special_token_41|>",
|
524 |
-
"lstrip": false,
|
525 |
-
"normalized": false,
|
526 |
-
"rstrip": false,
|
527 |
-
"single_word": false,
|
528 |
-
"special": true
|
529 |
-
},
|
530 |
-
"128050": {
|
531 |
-
"content": "<|reserved_special_token_42|>",
|
532 |
-
"lstrip": false,
|
533 |
-
"normalized": false,
|
534 |
-
"rstrip": false,
|
535 |
-
"single_word": false,
|
536 |
-
"special": true
|
537 |
-
},
|
538 |
-
"128051": {
|
539 |
-
"content": "<|reserved_special_token_43|>",
|
540 |
-
"lstrip": false,
|
541 |
-
"normalized": false,
|
542 |
-
"rstrip": false,
|
543 |
-
"single_word": false,
|
544 |
-
"special": true
|
545 |
-
},
|
546 |
-
"128052": {
|
547 |
-
"content": "<|reserved_special_token_44|>",
|
548 |
-
"lstrip": false,
|
549 |
-
"normalized": false,
|
550 |
-
"rstrip": false,
|
551 |
-
"single_word": false,
|
552 |
-
"special": true
|
553 |
-
},
|
554 |
-
"128053": {
|
555 |
-
"content": "<|reserved_special_token_45|>",
|
556 |
-
"lstrip": false,
|
557 |
-
"normalized": false,
|
558 |
-
"rstrip": false,
|
559 |
-
"single_word": false,
|
560 |
-
"special": true
|
561 |
-
},
|
562 |
-
"128054": {
|
563 |
-
"content": "<|reserved_special_token_46|>",
|
564 |
-
"lstrip": false,
|
565 |
-
"normalized": false,
|
566 |
-
"rstrip": false,
|
567 |
-
"single_word": false,
|
568 |
-
"special": true
|
569 |
-
},
|
570 |
-
"128055": {
|
571 |
-
"content": "<|reserved_special_token_47|>",
|
572 |
-
"lstrip": false,
|
573 |
-
"normalized": false,
|
574 |
-
"rstrip": false,
|
575 |
-
"single_word": false,
|
576 |
-
"special": true
|
577 |
-
},
|
578 |
-
"128056": {
|
579 |
-
"content": "<|reserved_special_token_48|>",
|
580 |
-
"lstrip": false,
|
581 |
-
"normalized": false,
|
582 |
-
"rstrip": false,
|
583 |
-
"single_word": false,
|
584 |
-
"special": true
|
585 |
-
},
|
586 |
-
"128057": {
|
587 |
-
"content": "<|reserved_special_token_49|>",
|
588 |
-
"lstrip": false,
|
589 |
-
"normalized": false,
|
590 |
-
"rstrip": false,
|
591 |
-
"single_word": false,
|
592 |
-
"special": true
|
593 |
-
},
|
594 |
-
"128058": {
|
595 |
-
"content": "<|reserved_special_token_50|>",
|
596 |
-
"lstrip": false,
|
597 |
-
"normalized": false,
|
598 |
-
"rstrip": false,
|
599 |
-
"single_word": false,
|
600 |
-
"special": true
|
601 |
-
},
|
602 |
-
"128059": {
|
603 |
-
"content": "<|reserved_special_token_51|>",
|
604 |
-
"lstrip": false,
|
605 |
-
"normalized": false,
|
606 |
-
"rstrip": false,
|
607 |
-
"single_word": false,
|
608 |
-
"special": true
|
609 |
-
},
|
610 |
-
"128060": {
|
611 |
-
"content": "<|reserved_special_token_52|>",
|
612 |
-
"lstrip": false,
|
613 |
-
"normalized": false,
|
614 |
-
"rstrip": false,
|
615 |
-
"single_word": false,
|
616 |
-
"special": true
|
617 |
-
},
|
618 |
-
"128061": {
|
619 |
-
"content": "<|reserved_special_token_53|>",
|
620 |
-
"lstrip": false,
|
621 |
-
"normalized": false,
|
622 |
-
"rstrip": false,
|
623 |
-
"single_word": false,
|
624 |
-
"special": true
|
625 |
-
},
|
626 |
-
"128062": {
|
627 |
-
"content": "<|reserved_special_token_54|>",
|
628 |
-
"lstrip": false,
|
629 |
-
"normalized": false,
|
630 |
-
"rstrip": false,
|
631 |
-
"single_word": false,
|
632 |
-
"special": true
|
633 |
-
},
|
634 |
-
"128063": {
|
635 |
-
"content": "<|reserved_special_token_55|>",
|
636 |
-
"lstrip": false,
|
637 |
-
"normalized": false,
|
638 |
-
"rstrip": false,
|
639 |
-
"single_word": false,
|
640 |
-
"special": true
|
641 |
-
},
|
642 |
-
"128064": {
|
643 |
-
"content": "<|reserved_special_token_56|>",
|
644 |
-
"lstrip": false,
|
645 |
-
"normalized": false,
|
646 |
-
"rstrip": false,
|
647 |
-
"single_word": false,
|
648 |
-
"special": true
|
649 |
-
},
|
650 |
-
"128065": {
|
651 |
-
"content": "<|reserved_special_token_57|>",
|
652 |
-
"lstrip": false,
|
653 |
-
"normalized": false,
|
654 |
-
"rstrip": false,
|
655 |
-
"single_word": false,
|
656 |
-
"special": true
|
657 |
-
},
|
658 |
-
"128066": {
|
659 |
-
"content": "<|reserved_special_token_58|>",
|
660 |
-
"lstrip": false,
|
661 |
-
"normalized": false,
|
662 |
-
"rstrip": false,
|
663 |
-
"single_word": false,
|
664 |
-
"special": true
|
665 |
-
},
|
666 |
-
"128067": {
|
667 |
-
"content": "<|reserved_special_token_59|>",
|
668 |
-
"lstrip": false,
|
669 |
-
"normalized": false,
|
670 |
-
"rstrip": false,
|
671 |
-
"single_word": false,
|
672 |
-
"special": true
|
673 |
-
},
|
674 |
-
"128068": {
|
675 |
-
"content": "<|reserved_special_token_60|>",
|
676 |
-
"lstrip": false,
|
677 |
-
"normalized": false,
|
678 |
-
"rstrip": false,
|
679 |
-
"single_word": false,
|
680 |
-
"special": true
|
681 |
-
},
|
682 |
-
"128069": {
|
683 |
-
"content": "<|reserved_special_token_61|>",
|
684 |
-
"lstrip": false,
|
685 |
-
"normalized": false,
|
686 |
-
"rstrip": false,
|
687 |
-
"single_word": false,
|
688 |
-
"special": true
|
689 |
-
},
|
690 |
-
"128070": {
|
691 |
-
"content": "<|reserved_special_token_62|>",
|
692 |
-
"lstrip": false,
|
693 |
-
"normalized": false,
|
694 |
-
"rstrip": false,
|
695 |
-
"single_word": false,
|
696 |
-
"special": true
|
697 |
-
},
|
698 |
-
"128071": {
|
699 |
-
"content": "<|reserved_special_token_63|>",
|
700 |
-
"lstrip": false,
|
701 |
-
"normalized": false,
|
702 |
-
"rstrip": false,
|
703 |
-
"single_word": false,
|
704 |
-
"special": true
|
705 |
-
},
|
706 |
-
"128072": {
|
707 |
-
"content": "<|reserved_special_token_64|>",
|
708 |
-
"lstrip": false,
|
709 |
-
"normalized": false,
|
710 |
-
"rstrip": false,
|
711 |
-
"single_word": false,
|
712 |
-
"special": true
|
713 |
-
},
|
714 |
-
"128073": {
|
715 |
-
"content": "<|reserved_special_token_65|>",
|
716 |
-
"lstrip": false,
|
717 |
-
"normalized": false,
|
718 |
-
"rstrip": false,
|
719 |
-
"single_word": false,
|
720 |
-
"special": true
|
721 |
-
},
|
722 |
-
"128074": {
|
723 |
-
"content": "<|reserved_special_token_66|>",
|
724 |
-
"lstrip": false,
|
725 |
-
"normalized": false,
|
726 |
-
"rstrip": false,
|
727 |
-
"single_word": false,
|
728 |
-
"special": true
|
729 |
-
},
|
730 |
-
"128075": {
|
731 |
-
"content": "<|reserved_special_token_67|>",
|
732 |
-
"lstrip": false,
|
733 |
-
"normalized": false,
|
734 |
-
"rstrip": false,
|
735 |
-
"single_word": false,
|
736 |
-
"special": true
|
737 |
-
},
|
738 |
-
"128076": {
|
739 |
-
"content": "<|reserved_special_token_68|>",
|
740 |
-
"lstrip": false,
|
741 |
-
"normalized": false,
|
742 |
-
"rstrip": false,
|
743 |
-
"single_word": false,
|
744 |
-
"special": true
|
745 |
-
},
|
746 |
-
"128077": {
|
747 |
-
"content": "<|reserved_special_token_69|>",
|
748 |
-
"lstrip": false,
|
749 |
-
"normalized": false,
|
750 |
-
"rstrip": false,
|
751 |
-
"single_word": false,
|
752 |
-
"special": true
|
753 |
-
},
|
754 |
-
"128078": {
|
755 |
-
"content": "<|reserved_special_token_70|>",
|
756 |
-
"lstrip": false,
|
757 |
-
"normalized": false,
|
758 |
-
"rstrip": false,
|
759 |
-
"single_word": false,
|
760 |
-
"special": true
|
761 |
-
},
|
762 |
-
"128079": {
|
763 |
-
"content": "<|reserved_special_token_71|>",
|
764 |
-
"lstrip": false,
|
765 |
-
"normalized": false,
|
766 |
-
"rstrip": false,
|
767 |
-
"single_word": false,
|
768 |
-
"special": true
|
769 |
-
},
|
770 |
-
"128080": {
|
771 |
-
"content": "<|reserved_special_token_72|>",
|
772 |
-
"lstrip": false,
|
773 |
-
"normalized": false,
|
774 |
-
"rstrip": false,
|
775 |
-
"single_word": false,
|
776 |
-
"special": true
|
777 |
-
},
|
778 |
-
"128081": {
|
779 |
-
"content": "<|reserved_special_token_73|>",
|
780 |
-
"lstrip": false,
|
781 |
-
"normalized": false,
|
782 |
-
"rstrip": false,
|
783 |
-
"single_word": false,
|
784 |
-
"special": true
|
785 |
-
},
|
786 |
-
"128082": {
|
787 |
-
"content": "<|reserved_special_token_74|>",
|
788 |
-
"lstrip": false,
|
789 |
-
"normalized": false,
|
790 |
-
"rstrip": false,
|
791 |
-
"single_word": false,
|
792 |
-
"special": true
|
793 |
-
},
|
794 |
-
"128083": {
|
795 |
-
"content": "<|reserved_special_token_75|>",
|
796 |
-
"lstrip": false,
|
797 |
-
"normalized": false,
|
798 |
-
"rstrip": false,
|
799 |
-
"single_word": false,
|
800 |
-
"special": true
|
801 |
-
},
|
802 |
-
"128084": {
|
803 |
-
"content": "<|reserved_special_token_76|>",
|
804 |
-
"lstrip": false,
|
805 |
-
"normalized": false,
|
806 |
-
"rstrip": false,
|
807 |
-
"single_word": false,
|
808 |
-
"special": true
|
809 |
-
},
|
810 |
-
"128085": {
|
811 |
-
"content": "<|reserved_special_token_77|>",
|
812 |
-
"lstrip": false,
|
813 |
-
"normalized": false,
|
814 |
-
"rstrip": false,
|
815 |
-
"single_word": false,
|
816 |
-
"special": true
|
817 |
-
},
|
818 |
-
"128086": {
|
819 |
-
"content": "<|reserved_special_token_78|>",
|
820 |
-
"lstrip": false,
|
821 |
-
"normalized": false,
|
822 |
-
"rstrip": false,
|
823 |
-
"single_word": false,
|
824 |
-
"special": true
|
825 |
-
},
|
826 |
-
"128087": {
|
827 |
-
"content": "<|reserved_special_token_79|>",
|
828 |
-
"lstrip": false,
|
829 |
-
"normalized": false,
|
830 |
-
"rstrip": false,
|
831 |
-
"single_word": false,
|
832 |
-
"special": true
|
833 |
-
},
|
834 |
-
"128088": {
|
835 |
-
"content": "<|reserved_special_token_80|>",
|
836 |
-
"lstrip": false,
|
837 |
-
"normalized": false,
|
838 |
-
"rstrip": false,
|
839 |
-
"single_word": false,
|
840 |
-
"special": true
|
841 |
-
},
|
842 |
-
"128089": {
|
843 |
-
"content": "<|reserved_special_token_81|>",
|
844 |
-
"lstrip": false,
|
845 |
-
"normalized": false,
|
846 |
-
"rstrip": false,
|
847 |
-
"single_word": false,
|
848 |
-
"special": true
|
849 |
-
},
|
850 |
-
"128090": {
|
851 |
-
"content": "<|reserved_special_token_82|>",
|
852 |
-
"lstrip": false,
|
853 |
-
"normalized": false,
|
854 |
-
"rstrip": false,
|
855 |
-
"single_word": false,
|
856 |
-
"special": true
|
857 |
-
},
|
858 |
-
"128091": {
|
859 |
-
"content": "<|reserved_special_token_83|>",
|
860 |
-
"lstrip": false,
|
861 |
-
"normalized": false,
|
862 |
-
"rstrip": false,
|
863 |
-
"single_word": false,
|
864 |
-
"special": true
|
865 |
-
},
|
866 |
-
"128092": {
|
867 |
-
"content": "<|reserved_special_token_84|>",
|
868 |
-
"lstrip": false,
|
869 |
-
"normalized": false,
|
870 |
-
"rstrip": false,
|
871 |
-
"single_word": false,
|
872 |
-
"special": true
|
873 |
-
},
|
874 |
-
"128093": {
|
875 |
-
"content": "<|reserved_special_token_85|>",
|
876 |
-
"lstrip": false,
|
877 |
-
"normalized": false,
|
878 |
-
"rstrip": false,
|
879 |
-
"single_word": false,
|
880 |
-
"special": true
|
881 |
-
},
|
882 |
-
"128094": {
|
883 |
-
"content": "<|reserved_special_token_86|>",
|
884 |
-
"lstrip": false,
|
885 |
-
"normalized": false,
|
886 |
-
"rstrip": false,
|
887 |
-
"single_word": false
|
|
|
86 |
|
87 |
Note: Our predictor design has improved since the arXiv paper release (We added a layer-norm to stabilize training). Further, to focus on the main predictor design and training-eval scripts, we have removed the ablation scripts. To reproduce the original results and predictor models, please checkout commit `0412fc24a3b770e4d82e6d7064a8172f24c5fcd3` and download the old models from [Drive Link](https://drive.google.com/drive/folders/1psNZ1SU0LaZJ-x5MQGH59CzYSmeT4yRf?usp=sharing).
|
88 |
|
89 |
+
For the latest, new models, try the huggingface integration. [Wandb-Logs](https://wandb.ai/akhauriyash/TrainTokenButler) for trained models.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|