[update] model
Browse files- README.md +363 -363
- config.json +34 -34
- pytorch_model.bin +2 -2
- special_tokens_map.json +0 -7
- tokenizer_config.json +54 -60
README.md
CHANGED
@@ -6,7 +6,7 @@ tags:
|
|
6 |
- sentence-similarity
|
7 |
- mteb
|
8 |
model-index:
|
9 |
-
- name: tao
|
10 |
results:
|
11 |
- task:
|
12 |
type: STS
|
@@ -18,17 +18,17 @@ model-index:
|
|
18 |
revision: None
|
19 |
metrics:
|
20 |
- type: cos_sim_pearson
|
21 |
-
value:
|
22 |
- type: cos_sim_spearman
|
23 |
-
value:
|
24 |
- type: euclidean_pearson
|
25 |
-
value:
|
26 |
- type: euclidean_spearman
|
27 |
-
value:
|
28 |
- type: manhattan_pearson
|
29 |
-
value:
|
30 |
- type: manhattan_spearman
|
31 |
-
value:
|
32 |
- task:
|
33 |
type: STS
|
34 |
dataset:
|
@@ -39,17 +39,17 @@ model-index:
|
|
39 |
revision: None
|
40 |
metrics:
|
41 |
- type: cos_sim_pearson
|
42 |
-
value:
|
43 |
- type: cos_sim_spearman
|
44 |
-
value:
|
45 |
- type: euclidean_pearson
|
46 |
-
value:
|
47 |
- type: euclidean_spearman
|
48 |
-
value:
|
49 |
- type: manhattan_pearson
|
50 |
-
value:
|
51 |
- type: manhattan_spearman
|
52 |
-
value:
|
53 |
- task:
|
54 |
type: Classification
|
55 |
dataset:
|
@@ -60,9 +60,9 @@ model-index:
|
|
60 |
revision: 1399c76144fd37290681b995c656ef9b2e06e26d
|
61 |
metrics:
|
62 |
- type: accuracy
|
63 |
-
value:
|
64 |
- type: f1
|
65 |
-
value: 39.
|
66 |
- task:
|
67 |
type: STS
|
68 |
dataset:
|
@@ -73,17 +73,17 @@ model-index:
|
|
73 |
revision: None
|
74 |
metrics:
|
75 |
- type: cos_sim_pearson
|
76 |
-
value:
|
77 |
- type: cos_sim_spearman
|
78 |
-
value: 65.
|
79 |
- type: euclidean_pearson
|
80 |
-
value:
|
81 |
- type: euclidean_spearman
|
82 |
-
value: 65.
|
83 |
- type: manhattan_pearson
|
84 |
-
value:
|
85 |
- type: manhattan_spearman
|
86 |
-
value: 65.
|
87 |
- task:
|
88 |
type: Clustering
|
89 |
dataset:
|
@@ -94,7 +94,7 @@ model-index:
|
|
94 |
revision: None
|
95 |
metrics:
|
96 |
- type: v_measure
|
97 |
-
value: 39.
|
98 |
- task:
|
99 |
type: Clustering
|
100 |
dataset:
|
@@ -105,7 +105,7 @@ model-index:
|
|
105 |
revision: None
|
106 |
metrics:
|
107 |
- type: v_measure
|
108 |
-
value:
|
109 |
- task:
|
110 |
type: Reranking
|
111 |
dataset:
|
@@ -116,9 +116,9 @@ model-index:
|
|
116 |
revision: None
|
117 |
metrics:
|
118 |
- type: map
|
119 |
-
value:
|
120 |
- type: mrr
|
121 |
-
value:
|
122 |
- task:
|
123 |
type: Reranking
|
124 |
dataset:
|
@@ -129,9 +129,9 @@ model-index:
|
|
129 |
revision: None
|
130 |
metrics:
|
131 |
- type: map
|
132 |
-
value: 85.
|
133 |
- type: mrr
|
134 |
-
value: 88.
|
135 |
- task:
|
136 |
type: Retrieval
|
137 |
dataset:
|
@@ -142,65 +142,65 @@ model-index:
|
|
142 |
revision: None
|
143 |
metrics:
|
144 |
- type: map_at_1
|
145 |
-
value: 24.
|
146 |
- type: map_at_10
|
147 |
-
value: 36.
|
148 |
- type: map_at_100
|
149 |
-
value: 38.
|
150 |
- type: map_at_1000
|
151 |
-
value: 38.
|
152 |
- type: map_at_3
|
153 |
-
value: 32.
|
154 |
- type: map_at_5
|
155 |
-
value: 34.
|
156 |
- type: mrr_at_1
|
157 |
-
value: 37.
|
158 |
- type: mrr_at_10
|
159 |
-
value: 45.
|
160 |
- type: mrr_at_100
|
161 |
-
value: 46.
|
162 |
- type: mrr_at_1000
|
163 |
-
value: 46.
|
164 |
- type: mrr_at_3
|
165 |
-
value: 42.
|
166 |
- type: mrr_at_5
|
167 |
-
value: 44.
|
168 |
- type: ndcg_at_1
|
169 |
-
value: 37.
|
170 |
- type: ndcg_at_10
|
171 |
-
value: 42.
|
172 |
- type: ndcg_at_100
|
173 |
-
value: 50.
|
174 |
- type: ndcg_at_1000
|
175 |
-
value: 52.
|
176 |
- type: ndcg_at_3
|
177 |
-
value: 37.
|
178 |
- type: ndcg_at_5
|
179 |
-
value: 39.
|
180 |
- type: precision_at_1
|
181 |
-
value: 37.
|
182 |
- type: precision_at_10
|
183 |
-
value: 9.
|
184 |
- type: precision_at_100
|
185 |
-
value: 1.
|
186 |
- type: precision_at_1000
|
187 |
value: 0.183
|
188 |
- type: precision_at_3
|
189 |
-
value: 21.
|
190 |
- type: precision_at_5
|
191 |
-
value: 15.
|
192 |
- type: recall_at_1
|
193 |
-
value: 24.
|
194 |
- type: recall_at_10
|
195 |
-
value: 52.
|
196 |
- type: recall_at_100
|
197 |
-
value: 83.
|
198 |
- type: recall_at_1000
|
199 |
-
value: 98.
|
200 |
- type: recall_at_3
|
201 |
-
value: 37.
|
202 |
- type: recall_at_5
|
203 |
-
value: 43.
|
204 |
- task:
|
205 |
type: PairClassification
|
206 |
dataset:
|
@@ -211,51 +211,51 @@ model-index:
|
|
211 |
revision: None
|
212 |
metrics:
|
213 |
- type: cos_sim_accuracy
|
214 |
-
value:
|
215 |
- type: cos_sim_ap
|
216 |
-
value:
|
217 |
- type: cos_sim_f1
|
218 |
-
value:
|
219 |
- type: cos_sim_precision
|
220 |
-
value:
|
221 |
- type: cos_sim_recall
|
222 |
-
value: 87.
|
223 |
- type: dot_accuracy
|
224 |
-
value:
|
225 |
- type: dot_ap
|
226 |
-
value:
|
227 |
- type: dot_f1
|
228 |
-
value:
|
229 |
- type: dot_precision
|
230 |
-
value:
|
231 |
- type: dot_recall
|
232 |
-
value: 87.
|
233 |
- type: euclidean_accuracy
|
234 |
-
value:
|
235 |
- type: euclidean_ap
|
236 |
-
value:
|
237 |
- type: euclidean_f1
|
238 |
-
value:
|
239 |
- type: euclidean_precision
|
240 |
-
value:
|
241 |
- type: euclidean_recall
|
242 |
-
value: 87.
|
243 |
- type: manhattan_accuracy
|
244 |
-
value:
|
245 |
- type: manhattan_ap
|
246 |
-
value:
|
247 |
- type: manhattan_f1
|
248 |
-
value:
|
249 |
- type: manhattan_precision
|
250 |
-
value:
|
251 |
- type: manhattan_recall
|
252 |
-
value:
|
253 |
- type: max_accuracy
|
254 |
-
value:
|
255 |
- type: max_ap
|
256 |
-
value:
|
257 |
- type: max_f1
|
258 |
-
value:
|
259 |
- task:
|
260 |
type: Retrieval
|
261 |
dataset:
|
@@ -266,65 +266,65 @@ model-index:
|
|
266 |
revision: None
|
267 |
metrics:
|
268 |
- type: map_at_1
|
269 |
-
value:
|
270 |
- type: map_at_10
|
271 |
-
value: 77.
|
272 |
- type: map_at_100
|
273 |
-
value:
|
274 |
- type: map_at_1000
|
275 |
-
value:
|
276 |
- type: map_at_3
|
277 |
-
value:
|
278 |
- type: map_at_5
|
279 |
-
value:
|
280 |
- type: mrr_at_1
|
281 |
-
value:
|
282 |
- type: mrr_at_10
|
283 |
-
value: 77.
|
284 |
- type: mrr_at_100
|
285 |
-
value:
|
286 |
- type: mrr_at_1000
|
287 |
-
value:
|
288 |
- type: mrr_at_3
|
289 |
-
value:
|
290 |
- type: mrr_at_5
|
291 |
-
value:
|
292 |
- type: ndcg_at_1
|
293 |
-
value:
|
294 |
- type: ndcg_at_10
|
295 |
-
value:
|
296 |
- type: ndcg_at_100
|
297 |
-
value: 82.
|
298 |
- type: ndcg_at_1000
|
299 |
-
value:
|
300 |
- type: ndcg_at_3
|
301 |
-
value:
|
302 |
- type: ndcg_at_5
|
303 |
-
value:
|
304 |
- type: precision_at_1
|
305 |
-
value:
|
306 |
- type: precision_at_10
|
307 |
-
value: 9.
|
308 |
- type: precision_at_100
|
309 |
-
value:
|
310 |
- type: precision_at_1000
|
311 |
value: 0.101
|
312 |
- type: precision_at_3
|
313 |
-
value:
|
314 |
- type: precision_at_5
|
315 |
-
value: 17.
|
316 |
- type: recall_at_1
|
317 |
-
value:
|
318 |
- type: recall_at_10
|
319 |
-
value: 92.
|
320 |
- type: recall_at_100
|
321 |
-
value:
|
322 |
- type: recall_at_1000
|
323 |
-
value: 99.
|
324 |
- type: recall_at_3
|
325 |
-
value: 83.
|
326 |
- type: recall_at_5
|
327 |
-
value:
|
328 |
- task:
|
329 |
type: Retrieval
|
330 |
dataset:
|
@@ -335,65 +335,65 @@ model-index:
|
|
335 |
revision: None
|
336 |
metrics:
|
337 |
- type: map_at_1
|
338 |
-
value: 25.
|
339 |
- type: map_at_10
|
340 |
-
value:
|
341 |
- type: map_at_100
|
342 |
-
value:
|
343 |
- type: map_at_1000
|
344 |
-
value:
|
345 |
- type: map_at_3
|
346 |
-
value:
|
347 |
- type: map_at_5
|
348 |
-
value:
|
349 |
- type: mrr_at_1
|
350 |
-
value:
|
351 |
- type: mrr_at_10
|
352 |
-
value:
|
353 |
- type: mrr_at_100
|
354 |
-
value:
|
355 |
- type: mrr_at_1000
|
356 |
-
value:
|
357 |
- type: mrr_at_3
|
358 |
-
value:
|
359 |
- type: mrr_at_5
|
360 |
-
value:
|
361 |
- type: ndcg_at_1
|
362 |
-
value:
|
363 |
- type: ndcg_at_10
|
364 |
-
value:
|
365 |
- type: ndcg_at_100
|
366 |
-
value:
|
367 |
- type: ndcg_at_1000
|
368 |
-
value:
|
369 |
- type: ndcg_at_3
|
370 |
-
value:
|
371 |
- type: ndcg_at_5
|
372 |
-
value:
|
373 |
- type: precision_at_1
|
374 |
-
value:
|
375 |
- type: precision_at_10
|
376 |
-
value:
|
377 |
- type: precision_at_100
|
378 |
-
value: 4.
|
379 |
- type: precision_at_1000
|
380 |
value: 0.48900000000000005
|
381 |
- type: precision_at_3
|
382 |
-
value:
|
383 |
- type: precision_at_5
|
384 |
-
value:
|
385 |
- type: recall_at_1
|
386 |
-
value: 25.
|
387 |
- type: recall_at_10
|
388 |
-
value:
|
389 |
- type: recall_at_100
|
390 |
-
value: 97.
|
391 |
- type: recall_at_1000
|
392 |
-
value: 99.
|
393 |
- type: recall_at_3
|
394 |
-
value:
|
395 |
- type: recall_at_5
|
396 |
-
value:
|
397 |
- task:
|
398 |
type: Retrieval
|
399 |
dataset:
|
@@ -404,65 +404,65 @@ model-index:
|
|
404 |
revision: None
|
405 |
metrics:
|
406 |
- type: map_at_1
|
407 |
-
value:
|
408 |
- type: map_at_10
|
409 |
-
value:
|
410 |
- type: map_at_100
|
411 |
-
value:
|
412 |
- type: map_at_1000
|
413 |
-
value:
|
414 |
- type: map_at_3
|
415 |
-
value:
|
416 |
- type: map_at_5
|
417 |
-
value:
|
418 |
- type: mrr_at_1
|
419 |
-
value:
|
420 |
- type: mrr_at_10
|
421 |
-
value:
|
422 |
- type: mrr_at_100
|
423 |
-
value:
|
424 |
- type: mrr_at_1000
|
425 |
-
value:
|
426 |
- type: mrr_at_3
|
427 |
-
value:
|
428 |
- type: mrr_at_5
|
429 |
-
value:
|
430 |
- type: ndcg_at_1
|
431 |
-
value:
|
432 |
- type: ndcg_at_10
|
433 |
-
value:
|
434 |
- type: ndcg_at_100
|
435 |
-
value:
|
436 |
- type: ndcg_at_1000
|
437 |
-
value:
|
438 |
- type: ndcg_at_3
|
439 |
-
value:
|
440 |
- type: ndcg_at_5
|
441 |
-
value:
|
442 |
- type: precision_at_1
|
443 |
-
value:
|
444 |
- type: precision_at_10
|
445 |
-
value:
|
446 |
- type: precision_at_100
|
447 |
-
value: 0.
|
448 |
- type: precision_at_1000
|
449 |
-
value: 0.
|
450 |
- type: precision_at_3
|
451 |
-
value: 21.
|
452 |
- type: precision_at_5
|
453 |
-
value: 14.
|
454 |
- type: recall_at_1
|
455 |
-
value:
|
456 |
- type: recall_at_10
|
457 |
-
value:
|
458 |
- type: recall_at_100
|
459 |
-
value:
|
460 |
- type: recall_at_1000
|
461 |
-
value: 96.
|
462 |
- type: recall_at_3
|
463 |
-
value:
|
464 |
- type: recall_at_5
|
465 |
-
value:
|
466 |
- task:
|
467 |
type: Classification
|
468 |
dataset:
|
@@ -473,9 +473,9 @@ model-index:
|
|
473 |
revision: None
|
474 |
metrics:
|
475 |
- type: accuracy
|
476 |
-
value:
|
477 |
- type: f1
|
478 |
-
value:
|
479 |
- task:
|
480 |
type: Classification
|
481 |
dataset:
|
@@ -486,11 +486,11 @@ model-index:
|
|
486 |
revision: None
|
487 |
metrics:
|
488 |
- type: accuracy
|
489 |
-
value:
|
490 |
- type: ap
|
491 |
-
value:
|
492 |
- type: f1
|
493 |
-
value: 81.
|
494 |
- task:
|
495 |
type: STS
|
496 |
dataset:
|
@@ -501,17 +501,17 @@ model-index:
|
|
501 |
revision: None
|
502 |
metrics:
|
503 |
- type: cos_sim_pearson
|
504 |
-
value:
|
505 |
- type: cos_sim_spearman
|
506 |
-
value: 77.
|
507 |
- type: euclidean_pearson
|
508 |
-
value: 76.
|
509 |
- type: euclidean_spearman
|
510 |
-
value: 77.
|
511 |
- type: manhattan_pearson
|
512 |
-
value: 76.
|
513 |
- type: manhattan_spearman
|
514 |
-
value: 77.
|
515 |
- task:
|
516 |
type: Reranking
|
517 |
dataset:
|
@@ -522,9 +522,9 @@ model-index:
|
|
522 |
revision: None
|
523 |
metrics:
|
524 |
- type: map
|
525 |
-
value:
|
526 |
- type: mrr
|
527 |
-
value:
|
528 |
- task:
|
529 |
type: Retrieval
|
530 |
dataset:
|
@@ -535,65 +535,65 @@ model-index:
|
|
535 |
revision: None
|
536 |
metrics:
|
537 |
- type: map_at_1
|
538 |
-
value: 66.
|
539 |
- type: map_at_10
|
540 |
-
value: 75.
|
541 |
- type: map_at_100
|
542 |
-
value: 75.
|
543 |
- type: map_at_1000
|
544 |
-
value: 75.
|
545 |
- type: map_at_3
|
546 |
-
value: 73.
|
547 |
- type: map_at_5
|
548 |
-
value:
|
549 |
- type: mrr_at_1
|
550 |
-
value: 68.
|
551 |
- type: mrr_at_10
|
552 |
-
value:
|
553 |
- type: mrr_at_100
|
554 |
-
value:
|
555 |
- type: mrr_at_1000
|
556 |
-
value:
|
557 |
- type: mrr_at_3
|
558 |
-
value: 74.
|
559 |
- type: mrr_at_5
|
560 |
-
value: 75.
|
561 |
- type: ndcg_at_1
|
562 |
-
value: 68.
|
563 |
- type: ndcg_at_10
|
564 |
-
value:
|
565 |
- type: ndcg_at_100
|
566 |
-
value: 80.
|
567 |
- type: ndcg_at_1000
|
568 |
-
value: 80.
|
569 |
- type: ndcg_at_3
|
570 |
-
value: 75.
|
571 |
- type: ndcg_at_5
|
572 |
-
value: 77.
|
573 |
- type: precision_at_1
|
574 |
-
value: 68.
|
575 |
- type: precision_at_10
|
576 |
-
value: 9.
|
577 |
- type: precision_at_100
|
578 |
-
value: 1.
|
579 |
- type: precision_at_1000
|
580 |
value: 0.105
|
581 |
- type: precision_at_3
|
582 |
-
value: 28.
|
583 |
- type: precision_at_5
|
584 |
-
value:
|
585 |
- type: recall_at_1
|
586 |
-
value: 66.
|
587 |
- type: recall_at_10
|
588 |
-
value: 89.
|
589 |
- type: recall_at_100
|
590 |
-
value: 96.
|
591 |
- type: recall_at_1000
|
592 |
-
value: 98.
|
593 |
- type: recall_at_3
|
594 |
-
value:
|
595 |
- type: recall_at_5
|
596 |
-
value:
|
597 |
- task:
|
598 |
type: Classification
|
599 |
dataset:
|
@@ -604,9 +604,9 @@ model-index:
|
|
604 |
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
|
605 |
metrics:
|
606 |
- type: accuracy
|
607 |
-
value: 68.
|
608 |
- type: f1
|
609 |
-
value:
|
610 |
- task:
|
611 |
type: Classification
|
612 |
dataset:
|
@@ -617,9 +617,9 @@ model-index:
|
|
617 |
revision: 7d571f92784cd94a019292a1f45445077d0ef634
|
618 |
metrics:
|
619 |
- type: accuracy
|
620 |
-
value:
|
621 |
- type: f1
|
622 |
-
value:
|
623 |
- task:
|
624 |
type: Retrieval
|
625 |
dataset:
|
@@ -630,65 +630,65 @@ model-index:
|
|
630 |
revision: None
|
631 |
metrics:
|
632 |
- type: map_at_1
|
633 |
-
value:
|
634 |
- type: map_at_10
|
635 |
-
value:
|
636 |
- type: map_at_100
|
637 |
-
value: 57.
|
638 |
- type: map_at_1000
|
639 |
-
value: 57.
|
640 |
- type: map_at_3
|
641 |
-
value: 55.
|
642 |
- type: map_at_5
|
643 |
-
value: 56.
|
644 |
- type: mrr_at_1
|
645 |
-
value:
|
646 |
- type: mrr_at_10
|
647 |
-
value:
|
648 |
- type: mrr_at_100
|
649 |
-
value: 57.
|
650 |
- type: mrr_at_1000
|
651 |
-
value: 57.
|
652 |
- type: mrr_at_3
|
653 |
-
value: 55.
|
654 |
- type: mrr_at_5
|
655 |
-
value: 56.
|
656 |
- type: ndcg_at_1
|
657 |
-
value:
|
658 |
- type: ndcg_at_10
|
659 |
-
value: 59.
|
660 |
- type: ndcg_at_100
|
661 |
-
value: 62.
|
662 |
- type: ndcg_at_1000
|
663 |
-
value: 64.
|
664 |
- type: ndcg_at_3
|
665 |
-
value:
|
666 |
- type: ndcg_at_5
|
667 |
-
value: 58.
|
668 |
- type: precision_at_1
|
669 |
-
value:
|
670 |
- type: precision_at_10
|
671 |
-
value: 6.
|
672 |
- type: precision_at_100
|
673 |
-
value: 0.
|
674 |
- type: precision_at_1000
|
675 |
-
value: 0.
|
676 |
- type: precision_at_3
|
677 |
-
value: 20.
|
678 |
- type: precision_at_5
|
679 |
-
value: 12.
|
680 |
- type: recall_at_1
|
681 |
-
value:
|
682 |
- type: recall_at_10
|
683 |
-
value: 68.
|
684 |
- type: recall_at_100
|
685 |
-
value:
|
686 |
- type: recall_at_1000
|
687 |
-
value: 95.
|
688 |
- type: recall_at_3
|
689 |
-
value: 61.
|
690 |
- type: recall_at_5
|
691 |
-
value: 64.
|
692 |
- task:
|
693 |
type: Classification
|
694 |
dataset:
|
@@ -699,9 +699,9 @@ model-index:
|
|
699 |
revision: None
|
700 |
metrics:
|
701 |
- type: accuracy
|
702 |
-
value: 73.
|
703 |
- type: f1
|
704 |
-
value: 72.
|
705 |
- task:
|
706 |
type: PairClassification
|
707 |
dataset:
|
@@ -712,51 +712,51 @@ model-index:
|
|
712 |
revision: None
|
713 |
metrics:
|
714 |
- type: cos_sim_accuracy
|
715 |
-
value:
|
716 |
- type: cos_sim_ap
|
717 |
-
value:
|
718 |
- type: cos_sim_f1
|
719 |
-
value:
|
720 |
- type: cos_sim_precision
|
721 |
-
value:
|
722 |
- type: cos_sim_recall
|
723 |
-
value:
|
724 |
- type: dot_accuracy
|
725 |
-
value:
|
726 |
- type: dot_ap
|
727 |
-
value:
|
728 |
- type: dot_f1
|
729 |
-
value:
|
730 |
- type: dot_precision
|
731 |
-
value:
|
732 |
- type: dot_recall
|
733 |
-
value:
|
734 |
- type: euclidean_accuracy
|
735 |
-
value:
|
736 |
- type: euclidean_ap
|
737 |
-
value:
|
738 |
- type: euclidean_f1
|
739 |
-
value:
|
740 |
- type: euclidean_precision
|
741 |
-
value:
|
742 |
- type: euclidean_recall
|
743 |
-
value:
|
744 |
- type: manhattan_accuracy
|
745 |
-
value:
|
746 |
- type: manhattan_ap
|
747 |
-
value:
|
748 |
- type: manhattan_f1
|
749 |
-
value:
|
750 |
- type: manhattan_precision
|
751 |
-
value:
|
752 |
- type: manhattan_recall
|
753 |
-
value:
|
754 |
- type: max_accuracy
|
755 |
-
value:
|
756 |
- type: max_ap
|
757 |
-
value:
|
758 |
- type: max_f1
|
759 |
-
value:
|
760 |
- task:
|
761 |
type: Classification
|
762 |
dataset:
|
@@ -767,11 +767,11 @@ model-index:
|
|
767 |
revision: None
|
768 |
metrics:
|
769 |
- type: accuracy
|
770 |
-
value: 91.
|
771 |
- type: ap
|
772 |
-
value: 89.
|
773 |
- type: f1
|
774 |
-
value: 91.
|
775 |
- task:
|
776 |
type: STS
|
777 |
dataset:
|
@@ -782,17 +782,17 @@ model-index:
|
|
782 |
revision: None
|
783 |
metrics:
|
784 |
- type: cos_sim_pearson
|
785 |
-
value:
|
786 |
- type: cos_sim_spearman
|
787 |
-
value:
|
788 |
- type: euclidean_pearson
|
789 |
-
value:
|
790 |
- type: euclidean_spearman
|
791 |
-
value:
|
792 |
- type: manhattan_pearson
|
793 |
-
value:
|
794 |
- type: manhattan_spearman
|
795 |
-
value:
|
796 |
- task:
|
797 |
type: STS
|
798 |
dataset:
|
@@ -803,17 +803,17 @@ model-index:
|
|
803 |
revision: None
|
804 |
metrics:
|
805 |
- type: cos_sim_pearson
|
806 |
-
value:
|
807 |
- type: cos_sim_spearman
|
808 |
-
value:
|
809 |
- type: euclidean_pearson
|
810 |
-
value: 37.
|
811 |
- type: euclidean_spearman
|
812 |
-
value:
|
813 |
- type: manhattan_pearson
|
814 |
-
value: 37.
|
815 |
- type: manhattan_spearman
|
816 |
-
value:
|
817 |
- task:
|
818 |
type: STS
|
819 |
dataset:
|
@@ -824,17 +824,17 @@ model-index:
|
|
824 |
revision: 6d1ba47164174a496b7fa5d3569dae26a6813b80
|
825 |
metrics:
|
826 |
- type: cos_sim_pearson
|
827 |
-
value:
|
828 |
- type: cos_sim_spearman
|
829 |
-
value:
|
830 |
- type: euclidean_pearson
|
831 |
-
value: 67.
|
832 |
- type: euclidean_spearman
|
833 |
-
value:
|
834 |
- type: manhattan_pearson
|
835 |
-
value: 67.
|
836 |
- type: manhattan_spearman
|
837 |
-
value:
|
838 |
- task:
|
839 |
type: STS
|
840 |
dataset:
|
@@ -845,17 +845,17 @@ model-index:
|
|
845 |
revision: None
|
846 |
metrics:
|
847 |
- type: cos_sim_pearson
|
848 |
-
value: 78.
|
849 |
- type: cos_sim_spearman
|
850 |
-
value:
|
851 |
- type: euclidean_pearson
|
852 |
-
value:
|
853 |
- type: euclidean_spearman
|
854 |
-
value:
|
855 |
- type: manhattan_pearson
|
856 |
-
value:
|
857 |
- type: manhattan_spearman
|
858 |
-
value:
|
859 |
- task:
|
860 |
type: Reranking
|
861 |
dataset:
|
@@ -866,9 +866,9 @@ model-index:
|
|
866 |
revision: None
|
867 |
metrics:
|
868 |
- type: map
|
869 |
-
value: 66.
|
870 |
- type: mrr
|
871 |
-
value: 76.
|
872 |
- task:
|
873 |
type: Retrieval
|
874 |
dataset:
|
@@ -879,65 +879,65 @@ model-index:
|
|
879 |
revision: None
|
880 |
metrics:
|
881 |
- type: map_at_1
|
882 |
-
value: 27.
|
883 |
- type: map_at_10
|
884 |
-
value:
|
885 |
- type: map_at_100
|
886 |
-
value: 80.
|
887 |
- type: map_at_1000
|
888 |
-
value: 80.
|
889 |
- type: map_at_3
|
890 |
-
value:
|
891 |
- type: map_at_5
|
892 |
-
value: 66.
|
893 |
- type: mrr_at_1
|
894 |
-
value:
|
895 |
- type: mrr_at_10
|
896 |
-
value: 92.
|
897 |
- type: mrr_at_100
|
898 |
-
value: 92.
|
899 |
- type: mrr_at_1000
|
900 |
-
value: 92.
|
901 |
- type: mrr_at_3
|
902 |
-
value:
|
903 |
- type: mrr_at_5
|
904 |
-
value: 92.
|
905 |
- type: ndcg_at_1
|
906 |
-
value:
|
907 |
- type: ndcg_at_10
|
908 |
-
value: 84.
|
909 |
- type: ndcg_at_100
|
910 |
-
value:
|
911 |
- type: ndcg_at_1000
|
912 |
-
value: 88.
|
913 |
- type: ndcg_at_3
|
914 |
-
value:
|
915 |
- type: ndcg_at_5
|
916 |
-
value: 84.
|
917 |
- type: precision_at_1
|
918 |
-
value:
|
919 |
- type: precision_at_10
|
920 |
-
value:
|
921 |
- type: precision_at_100
|
922 |
-
value: 5.
|
923 |
- type: precision_at_1000
|
924 |
value: 0.516
|
925 |
- type: precision_at_3
|
926 |
-
value: 75.
|
927 |
- type: precision_at_5
|
928 |
-
value:
|
929 |
- type: recall_at_1
|
930 |
-
value: 27.
|
931 |
- type: recall_at_10
|
932 |
-
value: 83.
|
933 |
- type: recall_at_100
|
934 |
-
value: 95.
|
935 |
- type: recall_at_1000
|
936 |
-
value: 98.
|
937 |
- type: recall_at_3
|
938 |
-
value: 55.
|
939 |
- type: recall_at_5
|
940 |
-
value: 69.
|
941 |
- task:
|
942 |
type: Classification
|
943 |
dataset:
|
@@ -948,9 +948,9 @@ model-index:
|
|
948 |
revision: None
|
949 |
metrics:
|
950 |
- type: accuracy
|
951 |
-
value:
|
952 |
- type: f1
|
953 |
-
value:
|
954 |
- task:
|
955 |
type: Clustering
|
956 |
dataset:
|
@@ -961,7 +961,7 @@ model-index:
|
|
961 |
revision: None
|
962 |
metrics:
|
963 |
- type: v_measure
|
964 |
-
value:
|
965 |
- task:
|
966 |
type: Clustering
|
967 |
dataset:
|
@@ -972,7 +972,7 @@ model-index:
|
|
972 |
revision: None
|
973 |
metrics:
|
974 |
- type: v_measure
|
975 |
-
value:
|
976 |
- task:
|
977 |
type: Retrieval
|
978 |
dataset:
|
@@ -983,65 +983,65 @@ model-index:
|
|
983 |
revision: None
|
984 |
metrics:
|
985 |
- type: map_at_1
|
986 |
-
value:
|
987 |
- type: map_at_10
|
988 |
-
value:
|
989 |
- type: map_at_100
|
990 |
-
value:
|
991 |
- type: map_at_1000
|
992 |
-
value:
|
993 |
- type: map_at_3
|
994 |
-
value:
|
995 |
- type: map_at_5
|
996 |
-
value:
|
997 |
- type: mrr_at_1
|
998 |
-
value:
|
999 |
- type: mrr_at_10
|
1000 |
-
value:
|
1001 |
- type: mrr_at_100
|
1002 |
-
value:
|
1003 |
- type: mrr_at_1000
|
1004 |
-
value:
|
1005 |
- type: mrr_at_3
|
1006 |
-
value:
|
1007 |
- type: mrr_at_5
|
1008 |
-
value:
|
1009 |
- type: ndcg_at_1
|
1010 |
-
value:
|
1011 |
- type: ndcg_at_10
|
1012 |
-
value:
|
1013 |
- type: ndcg_at_100
|
1014 |
-
value:
|
1015 |
- type: ndcg_at_1000
|
1016 |
-
value:
|
1017 |
- type: ndcg_at_3
|
1018 |
-
value:
|
1019 |
- type: ndcg_at_5
|
1020 |
-
value:
|
1021 |
- type: precision_at_1
|
1022 |
-
value:
|
1023 |
- type: precision_at_10
|
1024 |
-
value: 8.
|
1025 |
- type: precision_at_100
|
1026 |
-
value: 0.
|
1027 |
- type: precision_at_1000
|
1028 |
-
value: 0.
|
1029 |
- type: precision_at_3
|
1030 |
-
value:
|
1031 |
- type: precision_at_5
|
1032 |
-
value: 15.
|
1033 |
- type: recall_at_1
|
1034 |
-
value:
|
1035 |
- type: recall_at_10
|
1036 |
-
value:
|
1037 |
- type: recall_at_100
|
1038 |
-
value:
|
1039 |
- type: recall_at_1000
|
1040 |
-
value: 98.
|
1041 |
- type: recall_at_3
|
1042 |
-
value:
|
1043 |
- type: recall_at_5
|
1044 |
-
value:
|
1045 |
- task:
|
1046 |
type: Classification
|
1047 |
dataset:
|
@@ -1052,11 +1052,11 @@ model-index:
|
|
1052 |
revision: None
|
1053 |
metrics:
|
1054 |
- type: accuracy
|
1055 |
-
value:
|
1056 |
- type: ap
|
1057 |
-
value: 70.
|
1058 |
- type: f1
|
1059 |
-
value: 85.
|
1060 |
---
|
1061 |
|
1062 |
a try for emebdding model
|
|
|
6 |
- sentence-similarity
|
7 |
- mteb
|
8 |
model-index:
|
9 |
+
- name: tao
|
10 |
results:
|
11 |
- task:
|
12 |
type: STS
|
|
|
18 |
revision: None
|
19 |
metrics:
|
20 |
- type: cos_sim_pearson
|
21 |
+
value: 47.33752515292192
|
22 |
- type: cos_sim_spearman
|
23 |
+
value: 49.940772056837176
|
24 |
- type: euclidean_pearson
|
25 |
+
value: 48.12147487857213
|
26 |
- type: euclidean_spearman
|
27 |
+
value: 49.9407519488174
|
28 |
- type: manhattan_pearson
|
29 |
+
value: 48.07550286372865
|
30 |
- type: manhattan_spearman
|
31 |
+
value: 49.89535645392862
|
32 |
- task:
|
33 |
type: STS
|
34 |
dataset:
|
|
|
39 |
revision: None
|
40 |
metrics:
|
41 |
- type: cos_sim_pearson
|
42 |
+
value: 50.976865711125626
|
43 |
- type: cos_sim_spearman
|
44 |
+
value: 53.113084748593465
|
45 |
- type: euclidean_pearson
|
46 |
+
value: 55.1209592747571
|
47 |
- type: euclidean_spearman
|
48 |
+
value: 53.11308362230699
|
49 |
- type: manhattan_pearson
|
50 |
+
value: 55.09799309322416
|
51 |
- type: manhattan_spearman
|
52 |
+
value: 53.108059998577076
|
53 |
- task:
|
54 |
type: Classification
|
55 |
dataset:
|
|
|
60 |
revision: 1399c76144fd37290681b995c656ef9b2e06e26d
|
61 |
metrics:
|
62 |
- type: accuracy
|
63 |
+
value: 40.812
|
64 |
- type: f1
|
65 |
+
value: 39.02060856097395
|
66 |
- task:
|
67 |
type: STS
|
68 |
dataset:
|
|
|
73 |
revision: None
|
74 |
metrics:
|
75 |
- type: cos_sim_pearson
|
76 |
+
value: 62.84336868097746
|
77 |
- type: cos_sim_spearman
|
78 |
+
value: 65.540605433497
|
79 |
- type: euclidean_pearson
|
80 |
+
value: 64.08759819387913
|
81 |
- type: euclidean_spearman
|
82 |
+
value: 65.54060543369363
|
83 |
- type: manhattan_pearson
|
84 |
+
value: 64.09334283385029
|
85 |
- type: manhattan_spearman
|
86 |
+
value: 65.55376209169398
|
87 |
- task:
|
88 |
type: Clustering
|
89 |
dataset:
|
|
|
94 |
revision: None
|
95 |
metrics:
|
96 |
- type: v_measure
|
97 |
+
value: 39.964020691388505
|
98 |
- task:
|
99 |
type: Clustering
|
100 |
dataset:
|
|
|
105 |
revision: None
|
106 |
metrics:
|
107 |
- type: v_measure
|
108 |
+
value: 38.18628830038994
|
109 |
- task:
|
110 |
type: Reranking
|
111 |
dataset:
|
|
|
116 |
revision: None
|
117 |
metrics:
|
118 |
- type: map
|
119 |
+
value: 85.34294439514511
|
120 |
- type: mrr
|
121 |
+
value: 88.03849206349206
|
122 |
- task:
|
123 |
type: Reranking
|
124 |
dataset:
|
|
|
129 |
revision: None
|
130 |
metrics:
|
131 |
- type: map
|
132 |
+
value: 85.87127698007234
|
133 |
- type: mrr
|
134 |
+
value: 88.57980158730159
|
135 |
- task:
|
136 |
type: Retrieval
|
137 |
dataset:
|
|
|
142 |
revision: None
|
143 |
metrics:
|
144 |
- type: map_at_1
|
145 |
+
value: 24.484
|
146 |
- type: map_at_10
|
147 |
+
value: 36.3
|
148 |
- type: map_at_100
|
149 |
+
value: 38.181
|
150 |
- type: map_at_1000
|
151 |
+
value: 38.305
|
152 |
- type: map_at_3
|
153 |
+
value: 32.39
|
154 |
- type: map_at_5
|
155 |
+
value: 34.504000000000005
|
156 |
- type: mrr_at_1
|
157 |
+
value: 37.608999999999995
|
158 |
- type: mrr_at_10
|
159 |
+
value: 45.348
|
160 |
- type: mrr_at_100
|
161 |
+
value: 46.375
|
162 |
- type: mrr_at_1000
|
163 |
+
value: 46.425
|
164 |
- type: mrr_at_3
|
165 |
+
value: 42.969
|
166 |
- type: mrr_at_5
|
167 |
+
value: 44.285999999999994
|
168 |
- type: ndcg_at_1
|
169 |
+
value: 37.608999999999995
|
170 |
- type: ndcg_at_10
|
171 |
+
value: 42.675999999999995
|
172 |
- type: ndcg_at_100
|
173 |
+
value: 50.12799999999999
|
174 |
- type: ndcg_at_1000
|
175 |
+
value: 52.321
|
176 |
- type: ndcg_at_3
|
177 |
+
value: 37.864
|
178 |
- type: ndcg_at_5
|
179 |
+
value: 39.701
|
180 |
- type: precision_at_1
|
181 |
+
value: 37.608999999999995
|
182 |
- type: precision_at_10
|
183 |
+
value: 9.527
|
184 |
- type: precision_at_100
|
185 |
+
value: 1.555
|
186 |
- type: precision_at_1000
|
187 |
value: 0.183
|
188 |
- type: precision_at_3
|
189 |
+
value: 21.547
|
190 |
- type: precision_at_5
|
191 |
+
value: 15.504000000000001
|
192 |
- type: recall_at_1
|
193 |
+
value: 24.484
|
194 |
- type: recall_at_10
|
195 |
+
value: 52.43299999999999
|
196 |
- type: recall_at_100
|
197 |
+
value: 83.446
|
198 |
- type: recall_at_1000
|
199 |
+
value: 98.24199999999999
|
200 |
- type: recall_at_3
|
201 |
+
value: 37.653
|
202 |
- type: recall_at_5
|
203 |
+
value: 43.643
|
204 |
- task:
|
205 |
type: PairClassification
|
206 |
dataset:
|
|
|
211 |
revision: None
|
212 |
metrics:
|
213 |
- type: cos_sim_accuracy
|
214 |
+
value: 77.71497294046902
|
215 |
- type: cos_sim_ap
|
216 |
+
value: 86.84542027578229
|
217 |
- type: cos_sim_f1
|
218 |
+
value: 79.31987247608926
|
219 |
- type: cos_sim_precision
|
220 |
+
value: 72.70601987142022
|
221 |
- type: cos_sim_recall
|
222 |
+
value: 87.2574234276362
|
223 |
- type: dot_accuracy
|
224 |
+
value: 77.71497294046902
|
225 |
- type: dot_ap
|
226 |
+
value: 86.86514752961159
|
227 |
- type: dot_f1
|
228 |
+
value: 79.31987247608926
|
229 |
- type: dot_precision
|
230 |
+
value: 72.70601987142022
|
231 |
- type: dot_recall
|
232 |
+
value: 87.2574234276362
|
233 |
- type: euclidean_accuracy
|
234 |
+
value: 77.71497294046902
|
235 |
- type: euclidean_ap
|
236 |
+
value: 86.84541456571337
|
237 |
- type: euclidean_f1
|
238 |
+
value: 79.31987247608926
|
239 |
- type: euclidean_precision
|
240 |
+
value: 72.70601987142022
|
241 |
- type: euclidean_recall
|
242 |
+
value: 87.2574234276362
|
243 |
- type: manhattan_accuracy
|
244 |
+
value: 77.8111846061335
|
245 |
- type: manhattan_ap
|
246 |
+
value: 86.81148050422539
|
247 |
- type: manhattan_f1
|
248 |
+
value: 79.41176470588236
|
249 |
- type: manhattan_precision
|
250 |
+
value: 72.52173913043478
|
251 |
- type: manhattan_recall
|
252 |
+
value: 87.74842179097499
|
253 |
- type: max_accuracy
|
254 |
+
value: 77.8111846061335
|
255 |
- type: max_ap
|
256 |
+
value: 86.86514752961159
|
257 |
- type: max_f1
|
258 |
+
value: 79.41176470588236
|
259 |
- task:
|
260 |
type: Retrieval
|
261 |
dataset:
|
|
|
266 |
revision: None
|
267 |
metrics:
|
268 |
- type: map_at_1
|
269 |
+
value: 68.862
|
270 |
- type: map_at_10
|
271 |
+
value: 77.079
|
272 |
- type: map_at_100
|
273 |
+
value: 77.428
|
274 |
- type: map_at_1000
|
275 |
+
value: 77.432
|
276 |
- type: map_at_3
|
277 |
+
value: 75.40400000000001
|
278 |
- type: map_at_5
|
279 |
+
value: 76.227
|
280 |
- type: mrr_at_1
|
281 |
+
value: 69.02000000000001
|
282 |
- type: mrr_at_10
|
283 |
+
value: 77.04299999999999
|
284 |
- type: mrr_at_100
|
285 |
+
value: 77.391
|
286 |
- type: mrr_at_1000
|
287 |
+
value: 77.395
|
288 |
- type: mrr_at_3
|
289 |
+
value: 75.44800000000001
|
290 |
- type: mrr_at_5
|
291 |
+
value: 76.23299999999999
|
292 |
- type: ndcg_at_1
|
293 |
+
value: 69.02000000000001
|
294 |
- type: ndcg_at_10
|
295 |
+
value: 80.789
|
296 |
- type: ndcg_at_100
|
297 |
+
value: 82.27499999999999
|
298 |
- type: ndcg_at_1000
|
299 |
+
value: 82.381
|
300 |
- type: ndcg_at_3
|
301 |
+
value: 77.40599999999999
|
302 |
- type: ndcg_at_5
|
303 |
+
value: 78.87100000000001
|
304 |
- type: precision_at_1
|
305 |
+
value: 69.02000000000001
|
306 |
- type: precision_at_10
|
307 |
+
value: 9.336
|
308 |
- type: precision_at_100
|
309 |
+
value: 0.9990000000000001
|
310 |
- type: precision_at_1000
|
311 |
value: 0.101
|
312 |
- type: precision_at_3
|
313 |
+
value: 27.889000000000003
|
314 |
- type: precision_at_5
|
315 |
+
value: 17.492
|
316 |
- type: recall_at_1
|
317 |
+
value: 68.862
|
318 |
- type: recall_at_10
|
319 |
+
value: 92.308
|
320 |
- type: recall_at_100
|
321 |
+
value: 98.84100000000001
|
322 |
- type: recall_at_1000
|
323 |
+
value: 99.684
|
324 |
- type: recall_at_3
|
325 |
+
value: 83.087
|
326 |
- type: recall_at_5
|
327 |
+
value: 86.617
|
328 |
- task:
|
329 |
type: Retrieval
|
330 |
dataset:
|
|
|
335 |
revision: None
|
336 |
metrics:
|
337 |
- type: map_at_1
|
338 |
+
value: 25.063999999999997
|
339 |
- type: map_at_10
|
340 |
+
value: 78.014
|
341 |
- type: map_at_100
|
342 |
+
value: 81.021
|
343 |
- type: map_at_1000
|
344 |
+
value: 81.059
|
345 |
- type: map_at_3
|
346 |
+
value: 53.616
|
347 |
- type: map_at_5
|
348 |
+
value: 68.00399999999999
|
349 |
- type: mrr_at_1
|
350 |
+
value: 87.8
|
351 |
- type: mrr_at_10
|
352 |
+
value: 91.824
|
353 |
- type: mrr_at_100
|
354 |
+
value: 91.915
|
355 |
- type: mrr_at_1000
|
356 |
+
value: 91.917
|
357 |
- type: mrr_at_3
|
358 |
+
value: 91.525
|
359 |
- type: mrr_at_5
|
360 |
+
value: 91.752
|
361 |
- type: ndcg_at_1
|
362 |
+
value: 87.8
|
363 |
- type: ndcg_at_10
|
364 |
+
value: 85.74199999999999
|
365 |
- type: ndcg_at_100
|
366 |
+
value: 88.82900000000001
|
367 |
- type: ndcg_at_1000
|
368 |
+
value: 89.208
|
369 |
- type: ndcg_at_3
|
370 |
+
value: 84.206
|
371 |
- type: ndcg_at_5
|
372 |
+
value: 83.421
|
373 |
- type: precision_at_1
|
374 |
+
value: 87.8
|
375 |
- type: precision_at_10
|
376 |
+
value: 41.325
|
377 |
- type: precision_at_100
|
378 |
+
value: 4.8
|
379 |
- type: precision_at_1000
|
380 |
value: 0.48900000000000005
|
381 |
- type: precision_at_3
|
382 |
+
value: 75.783
|
383 |
- type: precision_at_5
|
384 |
+
value: 64.25999999999999
|
385 |
- type: recall_at_1
|
386 |
+
value: 25.063999999999997
|
387 |
- type: recall_at_10
|
388 |
+
value: 87.324
|
389 |
- type: recall_at_100
|
390 |
+
value: 97.261
|
391 |
- type: recall_at_1000
|
392 |
+
value: 99.309
|
393 |
- type: recall_at_3
|
394 |
+
value: 56.281000000000006
|
395 |
- type: recall_at_5
|
396 |
+
value: 73.467
|
397 |
- task:
|
398 |
type: Retrieval
|
399 |
dataset:
|
|
|
404 |
revision: None
|
405 |
metrics:
|
406 |
- type: map_at_1
|
407 |
+
value: 46.800000000000004
|
408 |
- type: map_at_10
|
409 |
+
value: 56.887
|
410 |
- type: map_at_100
|
411 |
+
value: 57.556
|
412 |
- type: map_at_1000
|
413 |
+
value: 57.582
|
414 |
- type: map_at_3
|
415 |
+
value: 54.15
|
416 |
- type: map_at_5
|
417 |
+
value: 55.825
|
418 |
- type: mrr_at_1
|
419 |
+
value: 46.800000000000004
|
420 |
- type: mrr_at_10
|
421 |
+
value: 56.887
|
422 |
- type: mrr_at_100
|
423 |
+
value: 57.556
|
424 |
- type: mrr_at_1000
|
425 |
+
value: 57.582
|
426 |
- type: mrr_at_3
|
427 |
+
value: 54.15
|
428 |
- type: mrr_at_5
|
429 |
+
value: 55.825
|
430 |
- type: ndcg_at_1
|
431 |
+
value: 46.800000000000004
|
432 |
- type: ndcg_at_10
|
433 |
+
value: 62.061
|
434 |
- type: ndcg_at_100
|
435 |
+
value: 65.042
|
436 |
- type: ndcg_at_1000
|
437 |
+
value: 65.658
|
438 |
- type: ndcg_at_3
|
439 |
+
value: 56.52700000000001
|
440 |
- type: ndcg_at_5
|
441 |
+
value: 59.518
|
442 |
- type: precision_at_1
|
443 |
+
value: 46.800000000000004
|
444 |
- type: precision_at_10
|
445 |
+
value: 7.84
|
446 |
- type: precision_at_100
|
447 |
+
value: 0.9169999999999999
|
448 |
- type: precision_at_1000
|
449 |
+
value: 0.096
|
450 |
- type: precision_at_3
|
451 |
+
value: 21.133
|
452 |
- type: precision_at_5
|
453 |
+
value: 14.12
|
454 |
- type: recall_at_1
|
455 |
+
value: 46.800000000000004
|
456 |
- type: recall_at_10
|
457 |
+
value: 78.4
|
458 |
- type: recall_at_100
|
459 |
+
value: 91.7
|
460 |
- type: recall_at_1000
|
461 |
+
value: 96.39999999999999
|
462 |
- type: recall_at_3
|
463 |
+
value: 63.4
|
464 |
- type: recall_at_5
|
465 |
+
value: 70.6
|
466 |
- task:
|
467 |
type: Classification
|
468 |
dataset:
|
|
|
473 |
revision: None
|
474 |
metrics:
|
475 |
- type: accuracy
|
476 |
+
value: 48.010773374374764
|
477 |
- type: f1
|
478 |
+
value: 35.25314495210735
|
479 |
- task:
|
480 |
type: Classification
|
481 |
dataset:
|
|
|
486 |
revision: None
|
487 |
metrics:
|
488 |
- type: accuracy
|
489 |
+
value: 87.01688555347093
|
490 |
- type: ap
|
491 |
+
value: 56.39167630414159
|
492 |
- type: f1
|
493 |
+
value: 81.91756262306008
|
494 |
- task:
|
495 |
type: STS
|
496 |
dataset:
|
|
|
501 |
revision: None
|
502 |
metrics:
|
503 |
- type: cos_sim_pearson
|
504 |
+
value: 71.17867432738112
|
505 |
- type: cos_sim_spearman
|
506 |
+
value: 77.47954247528372
|
507 |
- type: euclidean_pearson
|
508 |
+
value: 76.32408876437825
|
509 |
- type: euclidean_spearman
|
510 |
+
value: 77.47954025694959
|
511 |
- type: manhattan_pearson
|
512 |
+
value: 76.33345801575938
|
513 |
- type: manhattan_spearman
|
514 |
+
value: 77.48901582125997
|
515 |
- task:
|
516 |
type: Reranking
|
517 |
dataset:
|
|
|
522 |
revision: None
|
523 |
metrics:
|
524 |
- type: map
|
525 |
+
value: 27.96333052746654
|
526 |
- type: mrr
|
527 |
+
value: 26.92023809523809
|
528 |
- task:
|
529 |
type: Retrieval
|
530 |
dataset:
|
|
|
535 |
revision: None
|
536 |
metrics:
|
537 |
- type: map_at_1
|
538 |
+
value: 66.144
|
539 |
- type: map_at_10
|
540 |
+
value: 75.036
|
541 |
- type: map_at_100
|
542 |
+
value: 75.36
|
543 |
- type: map_at_1000
|
544 |
+
value: 75.371
|
545 |
- type: map_at_3
|
546 |
+
value: 73.258
|
547 |
- type: map_at_5
|
548 |
+
value: 74.369
|
549 |
- type: mrr_at_1
|
550 |
+
value: 68.381
|
551 |
- type: mrr_at_10
|
552 |
+
value: 75.633
|
553 |
- type: mrr_at_100
|
554 |
+
value: 75.91799999999999
|
555 |
- type: mrr_at_1000
|
556 |
+
value: 75.928
|
557 |
- type: mrr_at_3
|
558 |
+
value: 74.093
|
559 |
- type: mrr_at_5
|
560 |
+
value: 75.036
|
561 |
- type: ndcg_at_1
|
562 |
+
value: 68.381
|
563 |
- type: ndcg_at_10
|
564 |
+
value: 78.661
|
565 |
- type: ndcg_at_100
|
566 |
+
value: 80.15
|
567 |
- type: ndcg_at_1000
|
568 |
+
value: 80.456
|
569 |
- type: ndcg_at_3
|
570 |
+
value: 75.295
|
571 |
- type: ndcg_at_5
|
572 |
+
value: 77.14999999999999
|
573 |
- type: precision_at_1
|
574 |
+
value: 68.381
|
575 |
- type: precision_at_10
|
576 |
+
value: 9.481
|
577 |
- type: precision_at_100
|
578 |
+
value: 1.023
|
579 |
- type: precision_at_1000
|
580 |
value: 0.105
|
581 |
- type: precision_at_3
|
582 |
+
value: 28.309
|
583 |
- type: precision_at_5
|
584 |
+
value: 17.974
|
585 |
- type: recall_at_1
|
586 |
+
value: 66.144
|
587 |
- type: recall_at_10
|
588 |
+
value: 89.24499999999999
|
589 |
- type: recall_at_100
|
590 |
+
value: 96.032
|
591 |
- type: recall_at_1000
|
592 |
+
value: 98.437
|
593 |
- type: recall_at_3
|
594 |
+
value: 80.327
|
595 |
- type: recall_at_5
|
596 |
+
value: 84.733
|
597 |
- task:
|
598 |
type: Classification
|
599 |
dataset:
|
|
|
604 |
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
|
605 |
metrics:
|
606 |
- type: accuracy
|
607 |
+
value: 68.26832548755884
|
608 |
- type: f1
|
609 |
+
value: 65.97422207086723
|
610 |
- task:
|
611 |
type: Classification
|
612 |
dataset:
|
|
|
617 |
revision: 7d571f92784cd94a019292a1f45445077d0ef634
|
618 |
metrics:
|
619 |
- type: accuracy
|
620 |
+
value: 73.13046402151984
|
621 |
- type: f1
|
622 |
+
value: 72.69199129694121
|
623 |
- task:
|
624 |
type: Retrieval
|
625 |
dataset:
|
|
|
630 |
revision: None
|
631 |
metrics:
|
632 |
- type: map_at_1
|
633 |
+
value: 50.4
|
634 |
- type: map_at_10
|
635 |
+
value: 56.645
|
636 |
- type: map_at_100
|
637 |
+
value: 57.160999999999994
|
638 |
- type: map_at_1000
|
639 |
+
value: 57.218
|
640 |
- type: map_at_3
|
641 |
+
value: 55.383
|
642 |
- type: map_at_5
|
643 |
+
value: 56.08800000000001
|
644 |
- type: mrr_at_1
|
645 |
+
value: 50.6
|
646 |
- type: mrr_at_10
|
647 |
+
value: 56.745999999999995
|
648 |
- type: mrr_at_100
|
649 |
+
value: 57.262
|
650 |
- type: mrr_at_1000
|
651 |
+
value: 57.318999999999996
|
652 |
- type: mrr_at_3
|
653 |
+
value: 55.483000000000004
|
654 |
- type: mrr_at_5
|
655 |
+
value: 56.188
|
656 |
- type: ndcg_at_1
|
657 |
+
value: 50.4
|
658 |
- type: ndcg_at_10
|
659 |
+
value: 59.534
|
660 |
- type: ndcg_at_100
|
661 |
+
value: 62.400999999999996
|
662 |
- type: ndcg_at_1000
|
663 |
+
value: 64.01299999999999
|
664 |
- type: ndcg_at_3
|
665 |
+
value: 56.887
|
666 |
- type: ndcg_at_5
|
667 |
+
value: 58.160000000000004
|
668 |
- type: precision_at_1
|
669 |
+
value: 50.4
|
670 |
- type: precision_at_10
|
671 |
+
value: 6.859999999999999
|
672 |
- type: precision_at_100
|
673 |
+
value: 0.828
|
674 |
- type: precision_at_1000
|
675 |
+
value: 0.096
|
676 |
- type: precision_at_3
|
677 |
+
value: 20.4
|
678 |
- type: precision_at_5
|
679 |
+
value: 12.86
|
680 |
- type: recall_at_1
|
681 |
+
value: 50.4
|
682 |
- type: recall_at_10
|
683 |
+
value: 68.60000000000001
|
684 |
- type: recall_at_100
|
685 |
+
value: 82.8
|
686 |
- type: recall_at_1000
|
687 |
+
value: 95.7
|
688 |
- type: recall_at_3
|
689 |
+
value: 61.199999999999996
|
690 |
- type: recall_at_5
|
691 |
+
value: 64.3
|
692 |
- task:
|
693 |
type: Classification
|
694 |
dataset:
|
|
|
699 |
revision: None
|
700 |
metrics:
|
701 |
- type: accuracy
|
702 |
+
value: 73.39666666666666
|
703 |
- type: f1
|
704 |
+
value: 72.86349039489504
|
705 |
- task:
|
706 |
type: PairClassification
|
707 |
dataset:
|
|
|
712 |
revision: None
|
713 |
metrics:
|
714 |
- type: cos_sim_accuracy
|
715 |
+
value: 73.36220898754738
|
716 |
- type: cos_sim_ap
|
717 |
+
value: 78.50300066088354
|
718 |
- type: cos_sim_f1
|
719 |
+
value: 75.39370078740157
|
720 |
- type: cos_sim_precision
|
721 |
+
value: 70.59907834101382
|
722 |
- type: cos_sim_recall
|
723 |
+
value: 80.8870116156283
|
724 |
- type: dot_accuracy
|
725 |
+
value: 73.36220898754738
|
726 |
- type: dot_ap
|
727 |
+
value: 78.50300066088354
|
728 |
- type: dot_f1
|
729 |
+
value: 75.39370078740157
|
730 |
- type: dot_precision
|
731 |
+
value: 70.59907834101382
|
732 |
- type: dot_recall
|
733 |
+
value: 80.8870116156283
|
734 |
- type: euclidean_accuracy
|
735 |
+
value: 73.36220898754738
|
736 |
- type: euclidean_ap
|
737 |
+
value: 78.50300066088354
|
738 |
- type: euclidean_f1
|
739 |
+
value: 75.39370078740157
|
740 |
- type: euclidean_precision
|
741 |
+
value: 70.59907834101382
|
742 |
- type: euclidean_recall
|
743 |
+
value: 80.8870116156283
|
744 |
- type: manhattan_accuracy
|
745 |
+
value: 73.09149972929075
|
746 |
- type: manhattan_ap
|
747 |
+
value: 78.41160715817406
|
748 |
- type: manhattan_f1
|
749 |
+
value: 75.3623188405797
|
750 |
- type: manhattan_precision
|
751 |
+
value: 69.45681211041853
|
752 |
- type: manhattan_recall
|
753 |
+
value: 82.36536430834214
|
754 |
- type: max_accuracy
|
755 |
+
value: 73.36220898754738
|
756 |
- type: max_ap
|
757 |
+
value: 78.50300066088354
|
758 |
- type: max_f1
|
759 |
+
value: 75.39370078740157
|
760 |
- task:
|
761 |
type: Classification
|
762 |
dataset:
|
|
|
767 |
revision: None
|
768 |
metrics:
|
769 |
- type: accuracy
|
770 |
+
value: 91.82000000000001
|
771 |
- type: ap
|
772 |
+
value: 89.3671278896903
|
773 |
- type: f1
|
774 |
+
value: 91.8021970144045
|
775 |
- task:
|
776 |
type: STS
|
777 |
dataset:
|
|
|
782 |
revision: None
|
783 |
metrics:
|
784 |
- type: cos_sim_pearson
|
785 |
+
value: 30.07022294131062
|
786 |
- type: cos_sim_spearman
|
787 |
+
value: 36.21542804954441
|
788 |
- type: euclidean_pearson
|
789 |
+
value: 36.37841945307606
|
790 |
- type: euclidean_spearman
|
791 |
+
value: 36.215513214835546
|
792 |
- type: manhattan_pearson
|
793 |
+
value: 36.31755715017088
|
794 |
- type: manhattan_spearman
|
795 |
+
value: 36.16848256918425
|
796 |
- task:
|
797 |
type: STS
|
798 |
dataset:
|
|
|
803 |
revision: None
|
804 |
metrics:
|
805 |
- type: cos_sim_pearson
|
806 |
+
value: 36.779755871073505
|
807 |
- type: cos_sim_spearman
|
808 |
+
value: 38.736220679196606
|
809 |
- type: euclidean_pearson
|
810 |
+
value: 37.13356686891227
|
811 |
- type: euclidean_spearman
|
812 |
+
value: 38.73619198602118
|
813 |
- type: manhattan_pearson
|
814 |
+
value: 37.175466658530816
|
815 |
- type: manhattan_spearman
|
816 |
+
value: 38.74523158724344
|
817 |
- task:
|
818 |
type: STS
|
819 |
dataset:
|
|
|
824 |
revision: 6d1ba47164174a496b7fa5d3569dae26a6813b80
|
825 |
metrics:
|
826 |
- type: cos_sim_pearson
|
827 |
+
value: 65.9737863254904
|
828 |
- type: cos_sim_spearman
|
829 |
+
value: 68.88293545840186
|
830 |
- type: euclidean_pearson
|
831 |
+
value: 67.23730973929247
|
832 |
- type: euclidean_spearman
|
833 |
+
value: 68.88293545840186
|
834 |
- type: manhattan_pearson
|
835 |
+
value: 67.30647960940956
|
836 |
- type: manhattan_spearman
|
837 |
+
value: 68.90553460682702
|
838 |
- task:
|
839 |
type: STS
|
840 |
dataset:
|
|
|
845 |
revision: None
|
846 |
metrics:
|
847 |
- type: cos_sim_pearson
|
848 |
+
value: 78.99371432933002
|
849 |
- type: cos_sim_spearman
|
850 |
+
value: 79.36496709214312
|
851 |
- type: euclidean_pearson
|
852 |
+
value: 78.77721120706431
|
853 |
- type: euclidean_spearman
|
854 |
+
value: 79.36500761622595
|
855 |
- type: manhattan_pearson
|
856 |
+
value: 78.82503201285202
|
857 |
- type: manhattan_spearman
|
858 |
+
value: 79.43915548337401
|
859 |
- task:
|
860 |
type: Reranking
|
861 |
dataset:
|
|
|
866 |
revision: None
|
867 |
metrics:
|
868 |
- type: map
|
869 |
+
value: 66.38418982516941
|
870 |
- type: mrr
|
871 |
+
value: 76.09996131153883
|
872 |
- task:
|
873 |
type: Retrieval
|
874 |
dataset:
|
|
|
879 |
revision: None
|
880 |
metrics:
|
881 |
- type: map_at_1
|
882 |
+
value: 27.426000000000002
|
883 |
- type: map_at_10
|
884 |
+
value: 77.209
|
885 |
- type: map_at_100
|
886 |
+
value: 80.838
|
887 |
- type: map_at_1000
|
888 |
+
value: 80.903
|
889 |
- type: map_at_3
|
890 |
+
value: 54.196
|
891 |
- type: map_at_5
|
892 |
+
value: 66.664
|
893 |
- type: mrr_at_1
|
894 |
+
value: 90.049
|
895 |
- type: mrr_at_10
|
896 |
+
value: 92.482
|
897 |
- type: mrr_at_100
|
898 |
+
value: 92.568
|
899 |
- type: mrr_at_1000
|
900 |
+
value: 92.572
|
901 |
- type: mrr_at_3
|
902 |
+
value: 92.072
|
903 |
- type: mrr_at_5
|
904 |
+
value: 92.33
|
905 |
- type: ndcg_at_1
|
906 |
+
value: 90.049
|
907 |
- type: ndcg_at_10
|
908 |
+
value: 84.69200000000001
|
909 |
- type: ndcg_at_100
|
910 |
+
value: 88.25699999999999
|
911 |
- type: ndcg_at_1000
|
912 |
+
value: 88.896
|
913 |
- type: ndcg_at_3
|
914 |
+
value: 86.09700000000001
|
915 |
- type: ndcg_at_5
|
916 |
+
value: 84.68599999999999
|
917 |
- type: precision_at_1
|
918 |
+
value: 90.049
|
919 |
- type: precision_at_10
|
920 |
+
value: 42.142
|
921 |
- type: precision_at_100
|
922 |
+
value: 5.017
|
923 |
- type: precision_at_1000
|
924 |
value: 0.516
|
925 |
- type: precision_at_3
|
926 |
+
value: 75.358
|
927 |
- type: precision_at_5
|
928 |
+
value: 63.173
|
929 |
- type: recall_at_1
|
930 |
+
value: 27.426000000000002
|
931 |
- type: recall_at_10
|
932 |
+
value: 83.59400000000001
|
933 |
- type: recall_at_100
|
934 |
+
value: 95.21
|
935 |
- type: recall_at_1000
|
936 |
+
value: 98.503
|
937 |
- type: recall_at_3
|
938 |
+
value: 55.849000000000004
|
939 |
- type: recall_at_5
|
940 |
+
value: 69.986
|
941 |
- task:
|
942 |
type: Classification
|
943 |
dataset:
|
|
|
948 |
revision: None
|
949 |
metrics:
|
950 |
- type: accuracy
|
951 |
+
value: 51.925999999999995
|
952 |
- type: f1
|
953 |
+
value: 50.16867723626971
|
954 |
- task:
|
955 |
type: Clustering
|
956 |
dataset:
|
|
|
961 |
revision: None
|
962 |
metrics:
|
963 |
- type: v_measure
|
964 |
+
value: 60.738901671970005
|
965 |
- task:
|
966 |
type: Clustering
|
967 |
dataset:
|
|
|
972 |
revision: None
|
973 |
metrics:
|
974 |
- type: v_measure
|
975 |
+
value: 57.08563183138733
|
976 |
- task:
|
977 |
type: Retrieval
|
978 |
dataset:
|
|
|
983 |
revision: None
|
984 |
metrics:
|
985 |
- type: map_at_1
|
986 |
+
value: 52.0
|
987 |
- type: map_at_10
|
988 |
+
value: 62.956
|
989 |
- type: map_at_100
|
990 |
+
value: 63.491
|
991 |
- type: map_at_1000
|
992 |
+
value: 63.50599999999999
|
993 |
- type: map_at_3
|
994 |
+
value: 60.733000000000004
|
995 |
- type: map_at_5
|
996 |
+
value: 62.217999999999996
|
997 |
- type: mrr_at_1
|
998 |
+
value: 52.0
|
999 |
- type: mrr_at_10
|
1000 |
+
value: 62.956
|
1001 |
- type: mrr_at_100
|
1002 |
+
value: 63.491
|
1003 |
- type: mrr_at_1000
|
1004 |
+
value: 63.50599999999999
|
1005 |
- type: mrr_at_3
|
1006 |
+
value: 60.733000000000004
|
1007 |
- type: mrr_at_5
|
1008 |
+
value: 62.217999999999996
|
1009 |
- type: ndcg_at_1
|
1010 |
+
value: 52.0
|
1011 |
- type: ndcg_at_10
|
1012 |
+
value: 67.956
|
1013 |
- type: ndcg_at_100
|
1014 |
+
value: 70.536
|
1015 |
- type: ndcg_at_1000
|
1016 |
+
value: 70.908
|
1017 |
- type: ndcg_at_3
|
1018 |
+
value: 63.456999999999994
|
1019 |
- type: ndcg_at_5
|
1020 |
+
value: 66.155
|
1021 |
- type: precision_at_1
|
1022 |
+
value: 52.0
|
1023 |
- type: precision_at_10
|
1024 |
+
value: 8.35
|
1025 |
- type: precision_at_100
|
1026 |
+
value: 0.955
|
1027 |
- type: precision_at_1000
|
1028 |
+
value: 0.098
|
1029 |
- type: precision_at_3
|
1030 |
+
value: 23.767
|
1031 |
- type: precision_at_5
|
1032 |
+
value: 15.58
|
1033 |
- type: recall_at_1
|
1034 |
+
value: 52.0
|
1035 |
- type: recall_at_10
|
1036 |
+
value: 83.5
|
1037 |
- type: recall_at_100
|
1038 |
+
value: 95.5
|
1039 |
- type: recall_at_1000
|
1040 |
+
value: 98.4
|
1041 |
- type: recall_at_3
|
1042 |
+
value: 71.3
|
1043 |
- type: recall_at_5
|
1044 |
+
value: 77.9
|
1045 |
- task:
|
1046 |
type: Classification
|
1047 |
dataset:
|
|
|
1052 |
revision: None
|
1053 |
metrics:
|
1054 |
- type: accuracy
|
1055 |
+
value: 87.10000000000001
|
1056 |
- type: ap
|
1057 |
+
value: 70.81766065881429
|
1058 |
- type: f1
|
1059 |
+
value: 85.5323306120456
|
1060 |
---
|
1061 |
|
1062 |
a try for emebdding model
|
config.json
CHANGED
@@ -1,35 +1,35 @@
|
|
1 |
{
|
2 |
-
|
3 |
-
|
4 |
-
|
5 |
-
|
6 |
-
|
7 |
-
|
8 |
-
|
9 |
-
|
10 |
-
|
11 |
-
|
12 |
-
|
13 |
-
|
14 |
-
|
15 |
-
|
16 |
-
|
17 |
-
|
18 |
-
|
19 |
-
|
20 |
-
|
21 |
-
|
22 |
-
|
23 |
-
|
24 |
-
|
25 |
-
|
26 |
-
|
27 |
-
|
28 |
-
|
29 |
-
|
30 |
-
|
31 |
-
|
32 |
-
|
33 |
-
|
34 |
-
|
35 |
-
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "",
|
3 |
+
"architectures": [
|
4 |
+
"BertModel"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"directionality": "bidi",
|
10 |
+
"eos_token_id": 2,
|
11 |
+
"hidden_act": "gelu",
|
12 |
+
"hidden_dropout_prob": 0.1,
|
13 |
+
"hidden_size": 1024,
|
14 |
+
"initializer_range": 0.02,
|
15 |
+
"intermediate_size": 4096,
|
16 |
+
"layer_norm_eps": 1e-12,
|
17 |
+
"max_position_embeddings": 8192,
|
18 |
+
"model_type": "bert",
|
19 |
+
"num_attention_heads": 16,
|
20 |
+
"num_hidden_layers": 24,
|
21 |
+
"output_past": true,
|
22 |
+
"pad_token_id": 0,
|
23 |
+
"pooler_fc_size": 768,
|
24 |
+
"pooler_num_attention_heads": 12,
|
25 |
+
"pooler_num_fc_layers": 3,
|
26 |
+
"pooler_size_per_head": 128,
|
27 |
+
"pooler_type": "first_token_transform",
|
28 |
+
"position_embedding_type": "absolute",
|
29 |
+
"torch_dtype": "bfloat16",
|
30 |
+
"transformers_version": "4.34.0",
|
31 |
+
"type_vocab_size": 2,
|
32 |
+
"uniem_pooling_strategy": "last_mean",
|
33 |
+
"use_cache": true,
|
34 |
+
"vocab_size": 21128
|
35 |
+
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dde0de5cbb98d2ba84092eb2f983c3badf5a21749d59c7a9eebacaa552d2b15f
|
3 |
+
size 666971245
|
special_tokens_map.json
CHANGED
@@ -1,11 +1,4 @@
|
|
1 |
{
|
2 |
-
"additional_special_tokens": [
|
3 |
-
"[PAD]",
|
4 |
-
"[UNK]",
|
5 |
-
"[CLS]",
|
6 |
-
"[SEP]",
|
7 |
-
"[MASK]"
|
8 |
-
],
|
9 |
"cls_token": "[CLS]",
|
10 |
"mask_token": "[MASK]",
|
11 |
"pad_token": "[PAD]",
|
|
|
1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2 |
"cls_token": "[CLS]",
|
3 |
"mask_token": "[MASK]",
|
4 |
"pad_token": "[PAD]",
|
tokenizer_config.json
CHANGED
@@ -1,62 +1,56 @@
|
|
1 |
{
|
2 |
-
|
3 |
-
|
4 |
-
|
5 |
-
|
6 |
-
|
7 |
-
|
8 |
-
|
9 |
-
|
10 |
-
},
|
11 |
-
"100": {
|
12 |
-
"content": "[UNK]",
|
13 |
-
"lstrip": false,
|
14 |
-
"normalized": false,
|
15 |
-
"rstrip": false,
|
16 |
-
"single_word": false,
|
17 |
-
"special": true
|
18 |
-
},
|
19 |
-
"101": {
|
20 |
-
"content": "[CLS]",
|
21 |
-
"lstrip": false,
|
22 |
-
"normalized": false,
|
23 |
-
"rstrip": false,
|
24 |
-
"single_word": false,
|
25 |
-
"special": true
|
26 |
-
},
|
27 |
-
"102": {
|
28 |
-
"content": "[SEP]",
|
29 |
-
"lstrip": false,
|
30 |
-
"normalized": false,
|
31 |
-
"rstrip": false,
|
32 |
-
"single_word": false,
|
33 |
-
"special": true
|
34 |
-
},
|
35 |
-
"103": {
|
36 |
-
"content": "[MASK]",
|
37 |
-
"lstrip": false,
|
38 |
-
"normalized": false,
|
39 |
-
"rstrip": false,
|
40 |
-
"single_word": false,
|
41 |
-
"special": true
|
42 |
-
}
|
43 |
},
|
44 |
-
"
|
45 |
-
|
46 |
-
|
47 |
-
|
48 |
-
|
49 |
-
|
50 |
-
|
51 |
-
|
52 |
-
"
|
53 |
-
|
54 |
-
|
55 |
-
|
56 |
-
|
57 |
-
|
58 |
-
|
59 |
-
|
60 |
-
"
|
61 |
-
|
62 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "[PAD]",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
10 |
},
|
11 |
+
"100": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"101": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"102": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"103": {
|
36 |
+
"content": "[MASK]",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"additional_special_tokens": [],
|
45 |
+
"clean_up_tokenization_spaces": true,
|
46 |
+
"cls_token": "[CLS]",
|
47 |
+
"do_lower_case": true,
|
48 |
+
"mask_token": "[MASK]",
|
49 |
+
"model_max_length": 8192,
|
50 |
+
"pad_token": "[PAD]",
|
51 |
+
"sep_token": "[SEP]",
|
52 |
+
"strip_accents": null,
|
53 |
+
"tokenize_chinese_chars": true,
|
54 |
+
"tokenizer_class": "BertTokenizer",
|
55 |
+
"unk_token": "[UNK]"
|
56 |
+
}
|