Hugging Face's logo

Amu
/
tao

Sentence Similarity
sentence-transformers
PyTorch
Chinese
bert
feature-extraction
mteb
Eval Results
text-embeddings-inference
Inference Endpoints
Model card Files Community
1
Amu commited on
Commit
1a56eaa
•
1 Parent(s): d63189f

[add] README.md

Browse files
Files changed (1) hide show
  1. README.md +1058 -0
README.md ADDED
@@ -0,0 +1,1058 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - mteb
4
+ model-index:
5
+ - name: tao
6
+ results:
7
+ - task:
8
+ type: STS
9
+ dataset:
10
+ type: C-MTEB/AFQMC
11
+ name: MTEB AFQMC
12
+ config: default
13
+ split: validation
14
+ revision: None
15
+ metrics:
16
+ - type: cos_sim_pearson
17
+ value: 47.33752515292192
18
+ - type: cos_sim_spearman
19
+ value: 49.940772056837176
20
+ - type: euclidean_pearson
21
+ value: 48.12147487857213
22
+ - type: euclidean_spearman
23
+ value: 49.9407519488174
24
+ - type: manhattan_pearson
25
+ value: 48.07550286372865
26
+ - type: manhattan_spearman
27
+ value: 49.89535645392862
28
+ - task:
29
+ type: STS
30
+ dataset:
31
+ type: C-MTEB/ATEC
32
+ name: MTEB ATEC
33
+ config: default
34
+ split: test
35
+ revision: None
36
+ metrics:
37
+ - type: cos_sim_pearson
38
+ value: 50.976865711125626
39
+ - type: cos_sim_spearman
40
+ value: 53.113084748593465
41
+ - type: euclidean_pearson
42
+ value: 55.1209592747571
43
+ - type: euclidean_spearman
44
+ value: 53.11308362230699
45
+ - type: manhattan_pearson
46
+ value: 55.09799309322416
47
+ - type: manhattan_spearman
48
+ value: 53.108059998577076
49
+ - task:
50
+ type: Classification
51
+ dataset:
52
+ type: mteb/amazon_reviews_multi
53
+ name: MTEB AmazonReviewsClassification (zh)
54
+ config: zh
55
+ split: test
56
+ revision: 1399c76144fd37290681b995c656ef9b2e06e26d
57
+ metrics:
58
+ - type: accuracy
59
+ value: 40.812
60
+ - type: f1
61
+ value: 39.02060856097395
62
+ - task:
63
+ type: STS
64
+ dataset:
65
+ type: C-MTEB/BQ
66
+ name: MTEB BQ
67
+ config: default
68
+ split: test
69
+ revision: None
70
+ metrics:
71
+ - type: cos_sim_pearson
72
+ value: 62.84336868097746
73
+ - type: cos_sim_spearman
74
+ value: 65.540605433497
75
+ - type: euclidean_pearson
76
+ value: 64.08759819387913
77
+ - type: euclidean_spearman
78
+ value: 65.54060543369363
79
+ - type: manhattan_pearson
80
+ value: 64.09334283385029
81
+ - type: manhattan_spearman
82
+ value: 65.55376209169398
83
+ - task:
84
+ type: Clustering
85
+ dataset:
86
+ type: C-MTEB/CLSClusteringP2P
87
+ name: MTEB CLSClusteringP2P
88
+ config: default
89
+ split: test
90
+ revision: None
91
+ metrics:
92
+ - type: v_measure
93
+ value: 39.964020691388505
94
+ - task:
95
+ type: Clustering
96
+ dataset:
97
+ type: C-MTEB/CLSClusteringS2S
98
+ name: MTEB CLSClusteringS2S
99
+ config: default
100
+ split: test
101
+ revision: None
102
+ metrics:
103
+ - type: v_measure
104
+ value: 38.18628830038994
105
+ - task:
106
+ type: Reranking
107
+ dataset:
108
+ type: C-MTEB/CMedQAv1-reranking
109
+ name: MTEB CMedQAv1
110
+ config: default
111
+ split: test
112
+ revision: None
113
+ metrics:
114
+ - type: map
115
+ value: 85.34294439514511
116
+ - type: mrr
117
+ value: 88.03849206349206
118
+ - task:
119
+ type: Reranking
120
+ dataset:
121
+ type: C-MTEB/CMedQAv2-reranking
122
+ name: MTEB CMedQAv2
123
+ config: default
124
+ split: test
125
+ revision: None
126
+ metrics:
127
+ - type: map
128
+ value: 85.87127698007234
129
+ - type: mrr
130
+ value: 88.57980158730159
131
+ - task:
132
+ type: Retrieval
133
+ dataset:
134
+ type: C-MTEB/CmedqaRetrieval
135
+ name: MTEB CmedqaRetrieval
136
+ config: default
137
+ split: dev
138
+ revision: None
139
+ metrics:
140
+ - type: map_at_1
141
+ value: 24.484
142
+ - type: map_at_10
143
+ value: 36.3
144
+ - type: map_at_100
145
+ value: 38.181
146
+ - type: map_at_1000
147
+ value: 38.305
148
+ - type: map_at_3
149
+ value: 32.39
150
+ - type: map_at_5
151
+ value: 34.504000000000005
152
+ - type: mrr_at_1
153
+ value: 37.608999999999995
154
+ - type: mrr_at_10
155
+ value: 45.348
156
+ - type: mrr_at_100
157
+ value: 46.375
158
+ - type: mrr_at_1000
159
+ value: 46.425
160
+ - type: mrr_at_3
161
+ value: 42.969
162
+ - type: mrr_at_5
163
+ value: 44.285999999999994
164
+ - type: ndcg_at_1
165
+ value: 37.608999999999995
166
+ - type: ndcg_at_10
167
+ value: 42.675999999999995
168
+ - type: ndcg_at_100
169
+ value: 50.12799999999999
170
+ - type: ndcg_at_1000
171
+ value: 52.321
172
+ - type: ndcg_at_3
173
+ value: 37.864
174
+ - type: ndcg_at_5
175
+ value: 39.701
176
+ - type: precision_at_1
177
+ value: 37.608999999999995
178
+ - type: precision_at_10
179
+ value: 9.527
180
+ - type: precision_at_100
181
+ value: 1.555
182
+ - type: precision_at_1000
183
+ value: 0.183
184
+ - type: precision_at_3
185
+ value: 21.547
186
+ - type: precision_at_5
187
+ value: 15.504000000000001
188
+ - type: recall_at_1
189
+ value: 24.484
190
+ - type: recall_at_10
191
+ value: 52.43299999999999
192
+ - type: recall_at_100
193
+ value: 83.446
194
+ - type: recall_at_1000
195
+ value: 98.24199999999999
196
+ - type: recall_at_3
197
+ value: 37.653
198
+ - type: recall_at_5
199
+ value: 43.643
200
+ - task:
201
+ type: PairClassification
202
+ dataset:
203
+ type: C-MTEB/CMNLI
204
+ name: MTEB Cmnli
205
+ config: default
206
+ split: validation
207
+ revision: None
208
+ metrics:
209
+ - type: cos_sim_accuracy
210
+ value: 77.71497294046902
211
+ - type: cos_sim_ap
212
+ value: 86.84542027578229
213
+ - type: cos_sim_f1
214
+ value: 79.31987247608926
215
+ - type: cos_sim_precision
216
+ value: 72.70601987142022
217
+ - type: cos_sim_recall
218
+ value: 87.2574234276362
219
+ - type: dot_accuracy
220
+ value: 77.71497294046902
221
+ - type: dot_ap
222
+ value: 86.86514752961159
223
+ - type: dot_f1
224
+ value: 79.31987247608926
225
+ - type: dot_precision
226
+ value: 72.70601987142022
227
+ - type: dot_recall
228
+ value: 87.2574234276362
229
+ - type: euclidean_accuracy
230
+ value: 77.71497294046902
231
+ - type: euclidean_ap
232
+ value: 86.84541456571337
233
+ - type: euclidean_f1
234
+ value: 79.31987247608926
235
+ - type: euclidean_precision
236
+ value: 72.70601987142022
237
+ - type: euclidean_recall
238
+ value: 87.2574234276362
239
+ - type: manhattan_accuracy
240
+ value: 77.8111846061335
241
+ - type: manhattan_ap
242
+ value: 86.81148050422539
243
+ - type: manhattan_f1
244
+ value: 79.41176470588236
245
+ - type: manhattan_precision
246
+ value: 72.52173913043478
247
+ - type: manhattan_recall
248
+ value: 87.74842179097499
249
+ - type: max_accuracy
250
+ value: 77.8111846061335
251
+ - type: max_ap
252
+ value: 86.86514752961159
253
+ - type: max_f1
254
+ value: 79.41176470588236
255
+ - task:
256
+ type: Retrieval
257
+ dataset:
258
+ type: C-MTEB/CovidRetrieval
259
+ name: MTEB CovidRetrieval
260
+ config: default
261
+ split: dev
262
+ revision: None
263
+ metrics:
264
+ - type: map_at_1
265
+ value: 68.862
266
+ - type: map_at_10
267
+ value: 77.079
268
+ - type: map_at_100
269
+ value: 77.428
270
+ - type: map_at_1000
271
+ value: 77.432
272
+ - type: map_at_3
273
+ value: 75.40400000000001
274
+ - type: map_at_5
275
+ value: 76.227
276
+ - type: mrr_at_1
277
+ value: 69.02000000000001
278
+ - type: mrr_at_10
279
+ value: 77.04299999999999
280
+ - type: mrr_at_100
281
+ value: 77.391
282
+ - type: mrr_at_1000
283
+ value: 77.395
284
+ - type: mrr_at_3
285
+ value: 75.44800000000001
286
+ - type: mrr_at_5
287
+ value: 76.23299999999999
288
+ - type: ndcg_at_1
289
+ value: 69.02000000000001
290
+ - type: ndcg_at_10
291
+ value: 80.789
292
+ - type: ndcg_at_100
293
+ value: 82.27499999999999
294
+ - type: ndcg_at_1000
295
+ value: 82.381
296
+ - type: ndcg_at_3
297
+ value: 77.40599999999999
298
+ - type: ndcg_at_5
299
+ value: 78.87100000000001
300
+ - type: precision_at_1
301
+ value: 69.02000000000001
302
+ - type: precision_at_10
303
+ value: 9.336
304
+ - type: precision_at_100
305
+ value: 0.9990000000000001
306
+ - type: precision_at_1000
307
+ value: 0.101
308
+ - type: precision_at_3
309
+ value: 27.889000000000003
310
+ - type: precision_at_5
311
+ value: 17.492
312
+ - type: recall_at_1
313
+ value: 68.862
314
+ - type: recall_at_10
315
+ value: 92.308
316
+ - type: recall_at_100
317
+ value: 98.84100000000001
318
+ - type: recall_at_1000
319
+ value: 99.684
320
+ - type: recall_at_3
321
+ value: 83.087
322
+ - type: recall_at_5
323
+ value: 86.617
324
+ - task:
325
+ type: Retrieval
326
+ dataset:
327
+ type: C-MTEB/DuRetrieval
328
+ name: MTEB DuRetrieval
329
+ config: default
330
+ split: dev
331
+ revision: None
332
+ metrics:
333
+ - type: map_at_1
334
+ value: 25.063999999999997
335
+ - type: map_at_10
336
+ value: 78.014
337
+ - type: map_at_100
338
+ value: 81.021
339
+ - type: map_at_1000
340
+ value: 81.059
341
+ - type: map_at_3
342
+ value: 53.616
343
+ - type: map_at_5
344
+ value: 68.00399999999999
345
+ - type: mrr_at_1
346
+ value: 87.8
347
+ - type: mrr_at_10
348
+ value: 91.824
349
+ - type: mrr_at_100
350
+ value: 91.915
351
+ - type: mrr_at_1000
352
+ value: 91.917
353
+ - type: mrr_at_3
354
+ value: 91.525
355
+ - type: mrr_at_5
356
+ value: 91.752
357
+ - type: ndcg_at_1
358
+ value: 87.8
359
+ - type: ndcg_at_10
360
+ value: 85.74199999999999
361
+ - type: ndcg_at_100
362
+ value: 88.82900000000001
363
+ - type: ndcg_at_1000
364
+ value: 89.208
365
+ - type: ndcg_at_3
366
+ value: 84.206
367
+ - type: ndcg_at_5
368
+ value: 83.421
369
+ - type: precision_at_1
370
+ value: 87.8
371
+ - type: precision_at_10
372
+ value: 41.325
373
+ - type: precision_at_100
374
+ value: 4.8
375
+ - type: precision_at_1000
376
+ value: 0.48900000000000005
377
+ - type: precision_at_3
378
+ value: 75.783
379
+ - type: precision_at_5
380
+ value: 64.25999999999999
381
+ - type: recall_at_1
382
+ value: 25.063999999999997
383
+ - type: recall_at_10
384
+ value: 87.324
385
+ - type: recall_at_100
386
+ value: 97.261
387
+ - type: recall_at_1000
388
+ value: 99.309
389
+ - type: recall_at_3
390
+ value: 56.281000000000006
391
+ - type: recall_at_5
392
+ value: 73.467
393
+ - task:
394
+ type: Retrieval
395
+ dataset:
396
+ type: C-MTEB/EcomRetrieval
397
+ name: MTEB EcomRetrieval
398
+ config: default
399
+ split: dev
400
+ revision: None
401
+ metrics:
402
+ - type: map_at_1
403
+ value: 46.800000000000004
404
+ - type: map_at_10
405
+ value: 56.887
406
+ - type: map_at_100
407
+ value: 57.556
408
+ - type: map_at_1000
409
+ value: 57.582
410
+ - type: map_at_3
411
+ value: 54.15
412
+ - type: map_at_5
413
+ value: 55.825
414
+ - type: mrr_at_1
415
+ value: 46.800000000000004
416
+ - type: mrr_at_10
417
+ value: 56.887
418
+ - type: mrr_at_100
419
+ value: 57.556
420
+ - type: mrr_at_1000
421
+ value: 57.582
422
+ - type: mrr_at_3
423
+ value: 54.15
424
+ - type: mrr_at_5
425
+ value: 55.825
426
+ - type: ndcg_at_1
427
+ value: 46.800000000000004
428
+ - type: ndcg_at_10
429
+ value: 62.061
430
+ - type: ndcg_at_100
431
+ value: 65.042
432
+ - type: ndcg_at_1000
433
+ value: 65.658
434
+ - type: ndcg_at_3
435
+ value: 56.52700000000001
436
+ - type: ndcg_at_5
437
+ value: 59.518
438
+ - type: precision_at_1
439
+ value: 46.800000000000004
440
+ - type: precision_at_10
441
+ value: 7.84
442
+ - type: precision_at_100
443
+ value: 0.9169999999999999
444
+ - type: precision_at_1000
445
+ value: 0.096
446
+ - type: precision_at_3
447
+ value: 21.133
448
+ - type: precision_at_5
449
+ value: 14.12
450
+ - type: recall_at_1
451
+ value: 46.800000000000004
452
+ - type: recall_at_10
453
+ value: 78.4
454
+ - type: recall_at_100
455
+ value: 91.7
456
+ - type: recall_at_1000
457
+ value: 96.39999999999999
458
+ - type: recall_at_3
459
+ value: 63.4
460
+ - type: recall_at_5
461
+ value: 70.6
462
+ - task:
463
+ type: Classification
464
+ dataset:
465
+ type: C-MTEB/IFlyTek-classification
466
+ name: MTEB IFlyTek
467
+ config: default
468
+ split: validation
469
+ revision: None
470
+ metrics:
471
+ - type: accuracy
472
+ value: 48.010773374374764
473
+ - type: f1
474
+ value: 35.25314495210735
475
+ - task:
476
+ type: Classification
477
+ dataset:
478
+ type: C-MTEB/JDReview-classification
479
+ name: MTEB JDReview
480
+ config: default
481
+ split: test
482
+ revision: None
483
+ metrics:
484
+ - type: accuracy
485
+ value: 87.01688555347093
486
+ - type: ap
487
+ value: 56.39167630414159
488
+ - type: f1
489
+ value: 81.91756262306008
490
+ - task:
491
+ type: STS
492
+ dataset:
493
+ type: C-MTEB/LCQMC
494
+ name: MTEB LCQMC
495
+ config: default
496
+ split: test
497
+ revision: None
498
+ metrics:
499
+ - type: cos_sim_pearson
500
+ value: 71.17867432738112
501
+ - type: cos_sim_spearman
502
+ value: 77.47954247528372
503
+ - type: euclidean_pearson
504
+ value: 76.32408876437825
505
+ - type: euclidean_spearman
506
+ value: 77.47954025694959
507
+ - type: manhattan_pearson
508
+ value: 76.33345801575938
509
+ - type: manhattan_spearman
510
+ value: 77.48901582125997
511
+ - task:
512
+ type: Reranking
513
+ dataset:
514
+ type: C-MTEB/Mmarco-reranking
515
+ name: MTEB MMarcoReranking
516
+ config: default
517
+ split: dev
518
+ revision: None
519
+ metrics:
520
+ - type: map
521
+ value: 27.96333052746654
522
+ - type: mrr
523
+ value: 26.92023809523809
524
+ - task:
525
+ type: Retrieval
526
+ dataset:
527
+ type: C-MTEB/MMarcoRetrieval
528
+ name: MTEB MMarcoRetrieval
529
+ config: default
530
+ split: dev
531
+ revision: None
532
+ metrics:
533
+ - type: map_at_1
534
+ value: 66.144
535
+ - type: map_at_10
536
+ value: 75.036
537
+ - type: map_at_100
538
+ value: 75.36
539
+ - type: map_at_1000
540
+ value: 75.371
541
+ - type: map_at_3
542
+ value: 73.258
543
+ - type: map_at_5
544
+ value: 74.369
545
+ - type: mrr_at_1
546
+ value: 68.381
547
+ - type: mrr_at_10
548
+ value: 75.633
549
+ - type: mrr_at_100
550
+ value: 75.91799999999999
551
+ - type: mrr_at_1000
552
+ value: 75.928
553
+ - type: mrr_at_3
554
+ value: 74.093
555
+ - type: mrr_at_5
556
+ value: 75.036
557
+ - type: ndcg_at_1
558
+ value: 68.381
559
+ - type: ndcg_at_10
560
+ value: 78.661
561
+ - type: ndcg_at_100
562
+ value: 80.15
563
+ - type: ndcg_at_1000
564
+ value: 80.456
565
+ - type: ndcg_at_3
566
+ value: 75.295
567
+ - type: ndcg_at_5
568
+ value: 77.14999999999999
569
+ - type: precision_at_1
570
+ value: 68.381
571
+ - type: precision_at_10
572
+ value: 9.481
573
+ - type: precision_at_100
574
+ value: 1.023
575
+ - type: precision_at_1000
576
+ value: 0.105
577
+ - type: precision_at_3
578
+ value: 28.309
579
+ - type: precision_at_5
580
+ value: 17.974
581
+ - type: recall_at_1
582
+ value: 66.144
583
+ - type: recall_at_10
584
+ value: 89.24499999999999
585
+ - type: recall_at_100
586
+ value: 96.032
587
+ - type: recall_at_1000
588
+ value: 98.437
589
+ - type: recall_at_3
590
+ value: 80.327
591
+ - type: recall_at_5
592
+ value: 84.733
593
+ - task:
594
+ type: Classification
595
+ dataset:
596
+ type: mteb/amazon_massive_intent
597
+ name: MTEB MassiveIntentClassification (zh-CN)
598
+ config: zh-CN
599
+ split: test
600
+ revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
601
+ metrics:
602
+ - type: accuracy
603
+ value: 68.26832548755884
604
+ - type: f1
605
+ value: 65.97422207086723
606
+ - task:
607
+ type: Classification
608
+ dataset:
609
+ type: mteb/amazon_massive_scenario
610
+ name: MTEB MassiveScenarioClassification (zh-CN)
611
+ config: zh-CN
612
+ split: test
613
+ revision: 7d571f92784cd94a019292a1f45445077d0ef634
614
+ metrics:
615
+ - type: accuracy
616
+ value: 73.13046402151984
617
+ - type: f1
618
+ value: 72.69199129694121
619
+ - task:
620
+ type: Retrieval
621
+ dataset:
622
+ type: C-MTEB/MedicalRetrieval
623
+ name: MTEB MedicalRetrieval
624
+ config: default
625
+ split: dev
626
+ revision: None
627
+ metrics:
628
+ - type: map_at_1
629
+ value: 50.4
630
+ - type: map_at_10
631
+ value: 56.645
632
+ - type: map_at_100
633
+ value: 57.160999999999994
634
+ - type: map_at_1000
635
+ value: 57.218
636
+ - type: map_at_3
637
+ value: 55.383
638
+ - type: map_at_5
639
+ value: 56.08800000000001
640
+ - type: mrr_at_1
641
+ value: 50.6
642
+ - type: mrr_at_10
643
+ value: 56.745999999999995
644
+ - type: mrr_at_100
645
+ value: 57.262
646
+ - type: mrr_at_1000
647
+ value: 57.318999999999996
648
+ - type: mrr_at_3
649
+ value: 55.483000000000004
650
+ - type: mrr_at_5
651
+ value: 56.188
652
+ - type: ndcg_at_1
653
+ value: 50.4
654
+ - type: ndcg_at_10
655
+ value: 59.534
656
+ - type: ndcg_at_100
657
+ value: 62.400999999999996
658
+ - type: ndcg_at_1000
659
+ value: 64.01299999999999
660
+ - type: ndcg_at_3
661
+ value: 56.887
662
+ - type: ndcg_at_5
663
+ value: 58.160000000000004
664
+ - type: precision_at_1
665
+ value: 50.4
666
+ - type: precision_at_10
667
+ value: 6.859999999999999
668
+ - type: precision_at_100
669
+ value: 0.828
670
+ - type: precision_at_1000
671
+ value: 0.096
672
+ - type: precision_at_3
673
+ value: 20.4
674
+ - type: precision_at_5
675
+ value: 12.86
676
+ - type: recall_at_1
677
+ value: 50.4
678
+ - type: recall_at_10
679
+ value: 68.60000000000001
680
+ - type: recall_at_100
681
+ value: 82.8
682
+ - type: recall_at_1000
683
+ value: 95.7
684
+ - type: recall_at_3
685
+ value: 61.199999999999996
686
+ - type: recall_at_5
687
+ value: 64.3
688
+ - task:
689
+ type: Classification
690
+ dataset:
691
+ type: C-MTEB/MultilingualSentiment-classification
692
+ name: MTEB MultilingualSentiment
693
+ config: default
694
+ split: validation
695
+ revision: None
696
+ metrics:
697
+ - type: accuracy
698
+ value: 73.39666666666666
699
+ - type: f1
700
+ value: 72.86349039489504
701
+ - task:
702
+ type: PairClassification
703
+ dataset:
704
+ type: C-MTEB/OCNLI
705
+ name: MTEB Ocnli
706
+ config: default
707
+ split: validation
708
+ revision: None
709
+ metrics:
710
+ - type: cos_sim_accuracy
711
+ value: 73.36220898754738
712
+ - type: cos_sim_ap
713
+ value: 78.50300066088354
714
+ - type: cos_sim_f1
715
+ value: 75.39370078740157
716
+ - type: cos_sim_precision
717
+ value: 70.59907834101382
718
+ - type: cos_sim_recall
719
+ value: 80.8870116156283
720
+ - type: dot_accuracy
721
+ value: 73.36220898754738
722
+ - type: dot_ap
723
+ value: 78.50300066088354
724
+ - type: dot_f1
725
+ value: 75.39370078740157
726
+ - type: dot_precision
727
+ value: 70.59907834101382
728
+ - type: dot_recall
729
+ value: 80.8870116156283
730
+ - type: euclidean_accuracy
731
+ value: 73.36220898754738
732
+ - type: euclidean_ap
733
+ value: 78.50300066088354
734
+ - type: euclidean_f1
735
+ value: 75.39370078740157
736
+ - type: euclidean_precision
737
+ value: 70.59907834101382
738
+ - type: euclidean_recall
739
+ value: 80.8870116156283
740
+ - type: manhattan_accuracy
741
+ value: 73.09149972929075
742
+ - type: manhattan_ap
743
+ value: 78.41160715817406
744
+ - type: manhattan_f1
745
+ value: 75.3623188405797
746
+ - type: manhattan_precision
747
+ value: 69.45681211041853
748
+ - type: manhattan_recall
749
+ value: 82.36536430834214
750
+ - type: max_accuracy
751
+ value: 73.36220898754738
752
+ - type: max_ap
753
+ value: 78.50300066088354
754
+ - type: max_f1
755
+ value: 75.39370078740157
756
+ - task:
757
+ type: Classification
758
+ dataset:
759
+ type: C-MTEB/OnlineShopping-classification
760
+ name: MTEB OnlineShopping
761
+ config: default
762
+ split: test
763
+ revision: None
764
+ metrics:
765
+ - type: accuracy
766
+ value: 91.82000000000001
767
+ - type: ap
768
+ value: 89.3671278896903
769
+ - type: f1
770
+ value: 91.8021970144045
771
+ - task:
772
+ type: STS
773
+ dataset:
774
+ type: C-MTEB/PAWSX
775
+ name: MTEB PAWSX
776
+ config: default
777
+ split: test
778
+ revision: None
779
+ metrics:
780
+ - type: cos_sim_pearson
781
+ value: 30.07022294131062
782
+ - type: cos_sim_spearman
783
+ value: 36.21542804954441
784
+ - type: euclidean_pearson
785
+ value: 36.37841945307606
786
+ - type: euclidean_spearman
787
+ value: 36.215513214835546
788
+ - type: manhattan_pearson
789
+ value: 36.31755715017088
790
+ - type: manhattan_spearman
791
+ value: 36.16848256918425
792
+ - task:
793
+ type: STS
794
+ dataset:
795
+ type: C-MTEB/QBQTC
796
+ name: MTEB QBQTC
797
+ config: default
798
+ split: test
799
+ revision: None
800
+ metrics:
801
+ - type: cos_sim_pearson
802
+ value: 36.779755871073505
803
+ - type: cos_sim_spearman
804
+ value: 38.736220679196606
805
+ - type: euclidean_pearson
806
+ value: 37.13356686891227
807
+ - type: euclidean_spearman
808
+ value: 38.73619198602118
809
+ - type: manhattan_pearson
810
+ value: 37.175466658530816
811
+ - type: manhattan_spearman
812
+ value: 38.74523158724344
813
+ - task:
814
+ type: STS
815
+ dataset:
816
+ type: mteb/sts22-crosslingual-sts
817
+ name: MTEB STS22 (zh)
818
+ config: zh
819
+ split: test
820
+ revision: 6d1ba47164174a496b7fa5d3569dae26a6813b80
821
+ metrics:
822
+ - type: cos_sim_pearson
823
+ value: 65.9737863254904
824
+ - type: cos_sim_spearman
825
+ value: 68.88293545840186
826
+ - type: euclidean_pearson
827
+ value: 67.23730973929247
828
+ - type: euclidean_spearman
829
+ value: 68.88293545840186
830
+ - type: manhattan_pearson
831
+ value: 67.30647960940956
832
+ - type: manhattan_spearman
833
+ value: 68.90553460682702
834
+ - task:
835
+ type: STS
836
+ dataset:
837
+ type: C-MTEB/STSB
838
+ name: MTEB STSB
839
+ config: default
840
+ split: test
841
+ revision: None
842
+ metrics:
843
+ - type: cos_sim_pearson
844
+ value: 78.99371432933002
845
+ - type: cos_sim_spearman
846
+ value: 79.36496709214312
847
+ - type: euclidean_pearson
848
+ value: 78.77721120706431
849
+ - type: euclidean_spearman
850
+ value: 79.36500761622595
851
+ - type: manhattan_pearson
852
+ value: 78.82503201285202
853
+ - type: manhattan_spearman
854
+ value: 79.43915548337401
855
+ - task:
856
+ type: Reranking
857
+ dataset:
858
+ type: C-MTEB/T2Reranking
859
+ name: MTEB T2Reranking
860
+ config: default
861
+ split: dev
862
+ revision: None
863
+ metrics:
864
+ - type: map
865
+ value: 66.38418982516941
866
+ - type: mrr
867
+ value: 76.09996131153883
868
+ - task:
869
+ type: Retrieval
870
+ dataset:
871
+ type: C-MTEB/T2Retrieval
872
+ name: MTEB T2Retrieval
873
+ config: default
874
+ split: dev
875
+ revision: None
876
+ metrics:
877
+ - type: map_at_1
878
+ value: 27.426000000000002
879
+ - type: map_at_10
880
+ value: 77.209
881
+ - type: map_at_100
882
+ value: 80.838
883
+ - type: map_at_1000
884
+ value: 80.903
885
+ - type: map_at_3
886
+ value: 54.196
887
+ - type: map_at_5
888
+ value: 66.664
889
+ - type: mrr_at_1
890
+ value: 90.049
891
+ - type: mrr_at_10
892
+ value: 92.482
893
+ - type: mrr_at_100
894
+ value: 92.568
895
+ - type: mrr_at_1000
896
+ value: 92.572
897
+ - type: mrr_at_3
898
+ value: 92.072
899
+ - type: mrr_at_5
900
+ value: 92.33
901
+ - type: ndcg_at_1
902
+ value: 90.049
903
+ - type: ndcg_at_10
904
+ value: 84.69200000000001
905
+ - type: ndcg_at_100
906
+ value: 88.25699999999999
907
+ - type: ndcg_at_1000
908
+ value: 88.896
909
+ - type: ndcg_at_3
910
+ value: 86.09700000000001
911
+ - type: ndcg_at_5
912
+ value: 84.68599999999999
913
+ - type: precision_at_1
914
+ value: 90.049
915
+ - type: precision_at_10
916
+ value: 42.142
917
+ - type: precision_at_100
918
+ value: 5.017
919
+ - type: precision_at_1000
920
+ value: 0.516
921
+ - type: precision_at_3
922
+ value: 75.358
923
+ - type: precision_at_5
924
+ value: 63.173
925
+ - type: recall_at_1
926
+ value: 27.426000000000002
927
+ - type: recall_at_10
928
+ value: 83.59400000000001
929
+ - type: recall_at_100
930
+ value: 95.21
931
+ - type: recall_at_1000
932
+ value: 98.503
933
+ - type: recall_at_3
934
+ value: 55.849000000000004
935
+ - type: recall_at_5
936
+ value: 69.986
937
+ - task:
938
+ type: Classification
939
+ dataset:
940
+ type: C-MTEB/TNews-classification
941
+ name: MTEB TNews
942
+ config: default
943
+ split: validation
944
+ revision: None
945
+ metrics:
946
+ - type: accuracy
947
+ value: 51.925999999999995
948
+ - type: f1
949
+ value: 50.16867723626971
950
+ - task:
951
+ type: Clustering
952
+ dataset:
953
+ type: C-MTEB/ThuNewsClusteringP2P
954
+ name: MTEB ThuNewsClusteringP2P
955
+ config: default
956
+ split: test
957
+ revision: None
958
+ metrics:
959
+ - type: v_measure
960
+ value: 60.738901671970005
961
+ - task:
962
+ type: Clustering
963
+ dataset:
964
+ type: C-MTEB/ThuNewsClusteringS2S
965
+ name: MTEB ThuNewsClusteringS2S
966
+ config: default
967
+ split: test
968
+ revision: None
969
+ metrics:
970
+ - type: v_measure
971
+ value: 57.08563183138733
972
+ - task:
973
+ type: Retrieval
974
+ dataset:
975
+ type: C-MTEB/VideoRetrieval
976
+ name: MTEB VideoRetrieval
977
+ config: default
978
+ split: dev
979
+ revision: None
980
+ metrics:
981
+ - type: map_at_1
982
+ value: 52.0
983
+ - type: map_at_10
984
+ value: 62.956
985
+ - type: map_at_100
986
+ value: 63.491
987
+ - type: map_at_1000
988
+ value: 63.50599999999999
989
+ - type: map_at_3
990
+ value: 60.733000000000004
991
+ - type: map_at_5
992
+ value: 62.217999999999996
993
+ - type: mrr_at_1
994
+ value: 52.0
995
+ - type: mrr_at_10
996
+ value: 62.956
997
+ - type: mrr_at_100
998
+ value: 63.491
999
+ - type: mrr_at_1000
1000
+ value: 63.50599999999999
1001
+ - type: mrr_at_3
1002
+ value: 60.733000000000004
1003
+ - type: mrr_at_5
1004
+ value: 62.217999999999996
1005
+ - type: ndcg_at_1
1006
+ value: 52.0
1007
+ - type: ndcg_at_10
1008
+ value: 67.956
1009
+ - type: ndcg_at_100
1010
+ value: 70.536
1011
+ - type: ndcg_at_1000
1012
+ value: 70.908
1013
+ - type: ndcg_at_3
1014
+ value: 63.456999999999994
1015
+ - type: ndcg_at_5
1016
+ value: 66.155
1017
+ - type: precision_at_1
1018
+ value: 52.0
1019
+ - type: precision_at_10
1020
+ value: 8.35
1021
+ - type: precision_at_100
1022
+ value: 0.955
1023
+ - type: precision_at_1000
1024
+ value: 0.098
1025
+ - type: precision_at_3
1026
+ value: 23.767
1027
+ - type: precision_at_5
1028
+ value: 15.58
1029
+ - type: recall_at_1
1030
+ value: 52.0
1031
+ - type: recall_at_10
1032
+ value: 83.5
1033
+ - type: recall_at_100
1034
+ value: 95.5
1035
+ - type: recall_at_1000
1036
+ value: 98.4
1037
+ - type: recall_at_3
1038
+ value: 71.3
1039
+ - type: recall_at_5
1040
+ value: 77.9
1041
+ - task:
1042
+ type: Classification
1043
+ dataset:
1044
+ type: C-MTEB/waimai-classification
1045
+ name: MTEB Waimai
1046
+ config: default
1047
+ split: test
1048
+ revision: None
1049
+ metrics:
1050
+ - type: accuracy
1051
+ value: 87.10000000000001
1052
+ - type: ap
1053
+ value: 70.81766065881429
1054
+ - type: f1
1055
+ value: 85.5323306120456
1056
+ ---
1057
+
1058
+ a try for emebdding model