iampanda commited on
Commit
06b6787
1 Parent(s): 68814ce

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1072 -3
README.md CHANGED
@@ -1,3 +1,1072 @@
1
- ---
2
- license: mit
3
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - mteb
4
+ model-index:
5
+ - name: zpoint_large_embedding_zh
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: 56.52479321107392
18
+ - type: cos_sim_spearman
19
+ value: 60.72175935031135
20
+ - type: euclidean_pearson
21
+ value: 59.40990657564856
22
+ - type: euclidean_spearman
23
+ value: 60.72175934804556
24
+ - type: manhattan_pearson
25
+ value: 59.4134322847349
26
+ - type: manhattan_spearman
27
+ value: 60.724413114688225
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: 56.492631347325464
39
+ - type: cos_sim_spearman
40
+ value: 58.765171687177656
41
+ - type: euclidean_pearson
42
+ value: 63.236364373113844
43
+ - type: euclidean_spearman
44
+ value: 58.765171686714865
45
+ - type: manhattan_pearson
46
+ value: 63.22241814845751
47
+ - type: manhattan_spearman
48
+ value: 58.762780342648234
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: 49.72
60
+ - type: f1
61
+ value: 46.588683657317084
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: 73.07779128771674
73
+ - type: cos_sim_spearman
74
+ value: 75.03682691328844
75
+ - type: euclidean_pearson
76
+ value: 73.68098259699073
77
+ - type: euclidean_spearman
78
+ value: 75.03683037648963
79
+ - type: manhattan_pearson
80
+ value: 73.66963332679124
81
+ - type: manhattan_spearman
82
+ value: 75.02269337817758
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: 58.2897067752906
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: 48.79170511177673
105
+ - task:
106
+ type: Reranking
107
+ dataset:
108
+ type: C-MTEB/CMedQAv1
109
+ name: MTEB CMedQAv1
110
+ config: default
111
+ split: test
112
+ revision: None
113
+ metrics:
114
+ - type: map
115
+ value: 91.10738371185181
116
+ - type: mrr
117
+ value: 92.82496031746031
118
+ - task:
119
+ type: Reranking
120
+ dataset:
121
+ type: C-MTEB/CMedQAv2
122
+ name: MTEB CMedQAv2
123
+ config: default
124
+ split: test
125
+ revision: None
126
+ metrics:
127
+ - type: map
128
+ value: 90.06959035874831
129
+ - type: mrr
130
+ value: 92.00789682539683
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: 27.132
142
+ - type: map_at_10
143
+ value: 40.400999999999996
144
+ - type: map_at_100
145
+ value: 42.246
146
+ - type: map_at_1000
147
+ value: 42.351
148
+ - type: map_at_3
149
+ value: 35.94
150
+ - type: map_at_5
151
+ value: 38.527
152
+ - type: mrr_at_1
153
+ value: 41.285
154
+ - type: mrr_at_10
155
+ value: 49.474000000000004
156
+ - type: mrr_at_100
157
+ value: 50.4
158
+ - type: mrr_at_1000
159
+ value: 50.438
160
+ - type: mrr_at_3
161
+ value: 46.891
162
+ - type: mrr_at_5
163
+ value: 48.353
164
+ - type: ndcg_at_1
165
+ value: 41.285
166
+ - type: ndcg_at_10
167
+ value: 47.159
168
+ - type: ndcg_at_100
169
+ value: 54.163
170
+ - type: ndcg_at_1000
171
+ value: 55.921
172
+ - type: ndcg_at_3
173
+ value: 41.678
174
+ - type: ndcg_at_5
175
+ value: 44.069
176
+ - type: precision_at_1
177
+ value: 41.285
178
+ - type: precision_at_10
179
+ value: 10.468
180
+ - type: precision_at_100
181
+ value: 1.611
182
+ - type: precision_at_1000
183
+ value: 0.183
184
+ - type: precision_at_3
185
+ value: 23.648
186
+ - type: precision_at_5
187
+ value: 17.229
188
+ - type: recall_at_1
189
+ value: 27.132
190
+ - type: recall_at_10
191
+ value: 57.977999999999994
192
+ - type: recall_at_100
193
+ value: 86.88
194
+ - type: recall_at_1000
195
+ value: 98.586
196
+ - type: recall_at_3
197
+ value: 41.487
198
+ - type: recall_at_5
199
+ value: 48.79
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: 86.06133493686109
211
+ - type: cos_sim_ap
212
+ value: 92.54288511740305
213
+ - type: cos_sim_f1
214
+ value: 86.85572811163628
215
+ - type: cos_sim_precision
216
+ value: 83.72748969407681
217
+ - type: cos_sim_recall
218
+ value: 90.22679448211363
219
+ - type: dot_accuracy
220
+ value: 86.06133493686109
221
+ - type: dot_ap
222
+ value: 92.53922591080917
223
+ - type: dot_f1
224
+ value: 86.85572811163628
225
+ - type: dot_precision
226
+ value: 83.72748969407681
227
+ - type: dot_recall
228
+ value: 90.22679448211363
229
+ - type: euclidean_accuracy
230
+ value: 86.06133493686109
231
+ - type: euclidean_ap
232
+ value: 92.54287994398305
233
+ - type: euclidean_f1
234
+ value: 86.85572811163628
235
+ - type: euclidean_precision
236
+ value: 83.72748969407681
237
+ - type: euclidean_recall
238
+ value: 90.22679448211363
239
+ - type: manhattan_accuracy
240
+ value: 86.01322910402887
241
+ - type: manhattan_ap
242
+ value: 92.53060255301997
243
+ - type: manhattan_f1
244
+ value: 86.81441683456458
245
+ - type: manhattan_precision
246
+ value: 83.27249302125833
247
+ - type: manhattan_recall
248
+ value: 90.67103109656301
249
+ - type: max_accuracy
250
+ value: 86.06133493686109
251
+ - type: max_ap
252
+ value: 92.54288511740305
253
+ - type: max_f1
254
+ value: 86.85572811163628
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: 78.899
266
+ - type: map_at_10
267
+ value: 86.232
268
+ - type: map_at_100
269
+ value: 86.331
270
+ - type: map_at_1000
271
+ value: 86.332
272
+ - type: map_at_3
273
+ value: 85.256
274
+ - type: map_at_5
275
+ value: 85.883
276
+ - type: mrr_at_1
277
+ value: 79.347
278
+ - type: mrr_at_10
279
+ value: 86.252
280
+ - type: mrr_at_100
281
+ value: 86.342
282
+ - type: mrr_at_1000
283
+ value: 86.343
284
+ - type: mrr_at_3
285
+ value: 85.283
286
+ - type: mrr_at_5
287
+ value: 85.91
288
+ - type: ndcg_at_1
289
+ value: 79.347
290
+ - type: ndcg_at_10
291
+ value: 89.143
292
+ - type: ndcg_at_100
293
+ value: 89.541
294
+ - type: ndcg_at_1000
295
+ value: 89.58
296
+ - type: ndcg_at_3
297
+ value: 87.227
298
+ - type: ndcg_at_5
299
+ value: 88.31400000000001
300
+ - type: precision_at_1
301
+ value: 79.347
302
+ - type: precision_at_10
303
+ value: 9.905
304
+ - type: precision_at_100
305
+ value: 1.0070000000000001
306
+ - type: precision_at_1000
307
+ value: 0.101
308
+ - type: precision_at_3
309
+ value: 31.261
310
+ - type: precision_at_5
311
+ value: 19.305
312
+ - type: recall_at_1
313
+ value: 78.899
314
+ - type: recall_at_10
315
+ value: 97.99799999999999
316
+ - type: recall_at_100
317
+ value: 99.684
318
+ - type: recall_at_1000
319
+ value: 100.0
320
+ - type: recall_at_3
321
+ value: 92.808
322
+ - type: recall_at_5
323
+ value: 95.46900000000001
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: 27.107999999999997
335
+ - type: map_at_10
336
+ value: 82.525
337
+ - type: map_at_100
338
+ value: 85.168
339
+ - type: map_at_1000
340
+ value: 85.194
341
+ - type: map_at_3
342
+ value: 57.74399999999999
343
+ - type: map_at_5
344
+ value: 72.53699999999999
345
+ - type: mrr_at_1
346
+ value: 92.30000000000001
347
+ - type: mrr_at_10
348
+ value: 94.705
349
+ - type: mrr_at_100
350
+ value: 94.76599999999999
351
+ - type: mrr_at_1000
352
+ value: 94.76599999999999
353
+ - type: mrr_at_3
354
+ value: 94.55
355
+ - type: mrr_at_5
356
+ value: 94.64
357
+ - type: ndcg_at_1
358
+ value: 92.30000000000001
359
+ - type: ndcg_at_10
360
+ value: 89.23100000000001
361
+ - type: ndcg_at_100
362
+ value: 91.556
363
+ - type: ndcg_at_1000
364
+ value: 91.81700000000001
365
+ - type: ndcg_at_3
366
+ value: 88.558
367
+ - type: ndcg_at_5
368
+ value: 87.316
369
+ - type: precision_at_1
370
+ value: 92.30000000000001
371
+ - type: precision_at_10
372
+ value: 42.38
373
+ - type: precision_at_100
374
+ value: 4.818
375
+ - type: precision_at_1000
376
+ value: 0.488
377
+ - type: precision_at_3
378
+ value: 79.14999999999999
379
+ - type: precision_at_5
380
+ value: 66.63
381
+ - type: recall_at_1
382
+ value: 27.107999999999997
383
+ - type: recall_at_10
384
+ value: 89.914
385
+ - type: recall_at_100
386
+ value: 97.658
387
+ - type: recall_at_1000
388
+ value: 99.00099999999999
389
+ - type: recall_at_3
390
+ value: 59.673
391
+ - type: recall_at_5
392
+ value: 76.437
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: 55.00000000000001
404
+ - type: map_at_10
405
+ value: 65.57600000000001
406
+ - type: map_at_100
407
+ value: 66.096
408
+ - type: map_at_1000
409
+ value: 66.103
410
+ - type: map_at_3
411
+ value: 63.217
412
+ - type: map_at_5
413
+ value: 64.562
414
+ - type: mrr_at_1
415
+ value: 55.00000000000001
416
+ - type: mrr_at_10
417
+ value: 65.57600000000001
418
+ - type: mrr_at_100
419
+ value: 66.096
420
+ - type: mrr_at_1000
421
+ value: 66.103
422
+ - type: mrr_at_3
423
+ value: 63.217
424
+ - type: mrr_at_5
425
+ value: 64.562
426
+ - type: ndcg_at_1
427
+ value: 55.00000000000001
428
+ - type: ndcg_at_10
429
+ value: 70.74000000000001
430
+ - type: ndcg_at_100
431
+ value: 73.001
432
+ - type: ndcg_at_1000
433
+ value: 73.223
434
+ - type: ndcg_at_3
435
+ value: 65.837
436
+ - type: ndcg_at_5
437
+ value: 68.264
438
+ - type: precision_at_1
439
+ value: 55.00000000000001
440
+ - type: precision_at_10
441
+ value: 8.7
442
+ - type: precision_at_100
443
+ value: 0.97
444
+ - type: precision_at_1000
445
+ value: 0.099
446
+ - type: precision_at_3
447
+ value: 24.467
448
+ - type: precision_at_5
449
+ value: 15.86
450
+ - type: recall_at_1
451
+ value: 55.00000000000001
452
+ - type: recall_at_10
453
+ value: 87.0
454
+ - type: recall_at_100
455
+ value: 97.0
456
+ - type: recall_at_1000
457
+ value: 98.8
458
+ - type: recall_at_3
459
+ value: 73.4
460
+ - type: recall_at_5
461
+ value: 79.3
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: 51.696806464024625
473
+ - type: f1
474
+ value: 40.02655259854763
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: 88.87429643527206
486
+ - type: ap
487
+ value: 59.89821610336161
488
+ - type: f1
489
+ value: 83.98100504939507
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: 72.59510783330644
501
+ - type: cos_sim_spearman
502
+ value: 79.75022839599451
503
+ - type: euclidean_pearson
504
+ value: 79.54475341768782
505
+ - type: euclidean_spearman
506
+ value: 79.75021730266204
507
+ - type: manhattan_pearson
508
+ value: 79.53741020350834
509
+ - type: manhattan_spearman
510
+ value: 79.74152434784455
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: 38.86925357762224
522
+ - type: mrr
523
+ value: 38.17460317460318
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: 68.731
535
+ - type: map_at_10
536
+ value: 78.52
537
+ - type: map_at_100
538
+ value: 78.792
539
+ - type: map_at_1000
540
+ value: 78.797
541
+ - type: map_at_3
542
+ value: 76.586
543
+ - type: map_at_5
544
+ value: 77.876
545
+ - type: mrr_at_1
546
+ value: 71.003
547
+ - type: mrr_at_10
548
+ value: 79.03
549
+ - type: mrr_at_100
550
+ value: 79.27
551
+ - type: mrr_at_1000
552
+ value: 79.274
553
+ - type: mrr_at_3
554
+ value: 77.373
555
+ - type: mrr_at_5
556
+ value: 78.46600000000001
557
+ - type: ndcg_at_1
558
+ value: 71.003
559
+ - type: ndcg_at_10
560
+ value: 82.381
561
+ - type: ndcg_at_100
562
+ value: 83.504
563
+ - type: ndcg_at_1000
564
+ value: 83.627
565
+ - type: ndcg_at_3
566
+ value: 78.78699999999999
567
+ - type: ndcg_at_5
568
+ value: 80.94
569
+ - type: precision_at_1
570
+ value: 71.003
571
+ - type: precision_at_10
572
+ value: 9.961
573
+ - type: precision_at_100
574
+ value: 1.05
575
+ - type: precision_at_1000
576
+ value: 0.106
577
+ - type: precision_at_3
578
+ value: 29.694
579
+ - type: precision_at_5
580
+ value: 18.963
581
+ - type: recall_at_1
582
+ value: 68.731
583
+ - type: recall_at_10
584
+ value: 93.697
585
+ - type: recall_at_100
586
+ value: 98.546
587
+ - type: recall_at_1000
588
+ value: 99.515
589
+ - type: recall_at_3
590
+ value: 84.328
591
+ - type: recall_at_5
592
+ value: 89.42
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: 76.79219905850707
604
+ - type: f1
605
+ value: 73.15228001501512
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: 84.9562878278413
617
+ - type: f1
618
+ value: 84.0910677219451
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: 57.8
630
+ - type: map_at_10
631
+ value: 64.732
632
+ - type: map_at_100
633
+ value: 65.315
634
+ - type: map_at_1000
635
+ value: 65.347
636
+ - type: map_at_3
637
+ value: 63.14999999999999
638
+ - type: map_at_5
639
+ value: 63.934999999999995
640
+ - type: mrr_at_1
641
+ value: 57.99999999999999
642
+ - type: mrr_at_10
643
+ value: 64.852
644
+ - type: mrr_at_100
645
+ value: 65.435
646
+ - type: mrr_at_1000
647
+ value: 65.467
648
+ - type: mrr_at_3
649
+ value: 63.266999999999996
650
+ - type: mrr_at_5
651
+ value: 64.072
652
+ - type: ndcg_at_1
653
+ value: 57.8
654
+ - type: ndcg_at_10
655
+ value: 68.14
656
+ - type: ndcg_at_100
657
+ value: 71.04899999999999
658
+ - type: ndcg_at_1000
659
+ value: 71.856
660
+ - type: ndcg_at_3
661
+ value: 64.813
662
+ - type: ndcg_at_5
663
+ value: 66.241
664
+ - type: precision_at_1
665
+ value: 57.8
666
+ - type: precision_at_10
667
+ value: 7.89
668
+ - type: precision_at_100
669
+ value: 0.927
670
+ - type: precision_at_1000
671
+ value: 0.099
672
+ - type: precision_at_3
673
+ value: 23.200000000000003
674
+ - type: precision_at_5
675
+ value: 14.62
676
+ - type: recall_at_1
677
+ value: 57.8
678
+ - type: recall_at_10
679
+ value: 78.9
680
+ - type: recall_at_100
681
+ value: 92.7
682
+ - type: recall_at_1000
683
+ value: 99.0
684
+ - type: recall_at_3
685
+ value: 69.6
686
+ - type: recall_at_5
687
+ value: 73.1
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: 79.22333333333333
699
+ - type: f1
700
+ value: 79.01276765455862
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: 85.32755820249052
712
+ - type: cos_sim_ap
713
+ value: 90.56118966152913
714
+ - type: cos_sim_f1
715
+ value: 86.28428927680798
716
+ - type: cos_sim_precision
717
+ value: 81.75803402646503
718
+ - type: cos_sim_recall
719
+ value: 91.34107708553326
720
+ - type: dot_accuracy
721
+ value: 85.32755820249052
722
+ - type: dot_ap
723
+ value: 90.56120405888693
724
+ - type: dot_f1
725
+ value: 86.28428927680798
726
+ - type: dot_precision
727
+ value: 81.75803402646503
728
+ - type: dot_recall
729
+ value: 91.34107708553326
730
+ - type: euclidean_accuracy
731
+ value: 85.32755820249052
732
+ - type: euclidean_ap
733
+ value: 90.56118966152913
734
+ - type: euclidean_f1
735
+ value: 86.28428927680798
736
+ - type: euclidean_precision
737
+ value: 81.75803402646503
738
+ - type: euclidean_recall
739
+ value: 91.34107708553326
740
+ - type: manhattan_accuracy
741
+ value: 85.43584190579317
742
+ - type: manhattan_ap
743
+ value: 90.52296007826511
744
+ - type: manhattan_f1
745
+ value: 86.42099949520444
746
+ - type: manhattan_precision
747
+ value: 82.7852998065764
748
+ - type: manhattan_recall
749
+ value: 90.3907074973601
750
+ - type: max_accuracy
751
+ value: 85.43584190579317
752
+ - type: max_ap
753
+ value: 90.56120405888693
754
+ - type: max_f1
755
+ value: 86.42099949520444
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: 94.87999999999998
767
+ - type: ap
768
+ value: 93.12892276945414
769
+ - type: f1
770
+ value: 94.86921245385685
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: 38.4367277229591
782
+ - type: cos_sim_spearman
783
+ value: 45.942712312151656
784
+ - type: euclidean_pearson
785
+ value: 44.96055989566686
786
+ - type: euclidean_spearman
787
+ value: 45.94279939044163
788
+ - type: manhattan_pearson
789
+ value: 44.979762134562925
790
+ - type: manhattan_spearman
791
+ value: 45.96004430328375
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: 41.45428416733968
803
+ - type: cos_sim_spearman
804
+ value: 43.462057455255845
805
+ - type: euclidean_pearson
806
+ value: 38.20089604291246
807
+ - type: euclidean_spearman
808
+ value: 43.46288438624811
809
+ - type: manhattan_pearson
810
+ value: 38.175045608320694
811
+ - type: manhattan_spearman
812
+ value: 43.468885824666344
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: 65.61911213187778
824
+ - type: cos_sim_spearman
825
+ value: 66.70525921118497
826
+ - type: euclidean_pearson
827
+ value: 65.35554462551515
828
+ - type: euclidean_spearman
829
+ value: 66.70525921118497
830
+ - type: manhattan_pearson
831
+ value: 65.25174169329627
832
+ - type: manhattan_spearman
833
+ value: 66.6550752269368
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: 81.27160581568329
845
+ - type: cos_sim_spearman
846
+ value: 83.34482829304406
847
+ - type: euclidean_pearson
848
+ value: 82.98079434913451
849
+ - type: euclidean_spearman
850
+ value: 83.34503180775212
851
+ - type: manhattan_pearson
852
+ value: 82.95256917013506
853
+ - type: manhattan_spearman
854
+ value: 83.31034894907503
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: 69.29054152015013
866
+ - type: mrr
867
+ value: 79.73472208788729
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: 27.0
879
+ - type: map_at_10
880
+ value: 75.871
881
+ - type: map_at_100
882
+ value: 79.664
883
+ - type: map_at_1000
884
+ value: 79.725
885
+ - type: map_at_3
886
+ value: 53.14
887
+ - type: map_at_5
888
+ value: 65.365
889
+ - type: mrr_at_1
890
+ value: 88.642
891
+ - type: mrr_at_10
892
+ value: 91.732
893
+ - type: mrr_at_100
894
+ value: 91.818
895
+ - type: mrr_at_1000
896
+ value: 91.821
897
+ - type: mrr_at_3
898
+ value: 91.217
899
+ - type: mrr_at_5
900
+ value: 91.561
901
+ - type: ndcg_at_1
902
+ value: 88.642
903
+ - type: ndcg_at_10
904
+ value: 83.815
905
+ - type: ndcg_at_100
906
+ value: 87.689
907
+ - type: ndcg_at_1000
908
+ value: 88.266
909
+ - type: ndcg_at_3
910
+ value: 84.807
911
+ - type: ndcg_at_5
912
+ value: 83.53699999999999
913
+ - type: precision_at_1
914
+ value: 88.642
915
+ - type: precision_at_10
916
+ value: 41.725
917
+ - type: precision_at_100
918
+ value: 5.024
919
+ - type: precision_at_1000
920
+ value: 0.516
921
+ - type: precision_at_3
922
+ value: 74.10600000000001
923
+ - type: precision_at_5
924
+ value: 62.192
925
+ - type: recall_at_1
926
+ value: 27.0
927
+ - type: recall_at_10
928
+ value: 83.292
929
+ - type: recall_at_100
930
+ value: 95.66799999999999
931
+ - type: recall_at_1000
932
+ value: 98.56
933
+ - type: recall_at_3
934
+ value: 55.111
935
+ - type: recall_at_5
936
+ value: 69.327
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: 54.346
948
+ - type: f1
949
+ value: 52.302508458396055
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: 72.47709523787981
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: 69.35293863978707
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: 64.60000000000001
983
+ - type: map_at_10
984
+ value: 75.683
985
+ - type: map_at_100
986
+ value: 75.961
987
+ - type: map_at_1000
988
+ value: 75.96199999999999
989
+ - type: map_at_3
990
+ value: 74.083
991
+ - type: map_at_5
992
+ value: 75.03800000000001
993
+ - type: mrr_at_1
994
+ value: 64.60000000000001
995
+ - type: mrr_at_10
996
+ value: 75.683
997
+ - type: mrr_at_100
998
+ value: 75.961
999
+ - type: mrr_at_1000
1000
+ value: 75.96199999999999
1001
+ - type: mrr_at_3
1002
+ value: 74.083
1003
+ - type: mrr_at_5
1004
+ value: 75.03800000000001
1005
+ - type: ndcg_at_1
1006
+ value: 64.60000000000001
1007
+ - type: ndcg_at_10
1008
+ value: 80.26299999999999
1009
+ - type: ndcg_at_100
1010
+ value: 81.487
1011
+ - type: ndcg_at_1000
1012
+ value: 81.5
1013
+ - type: ndcg_at_3
1014
+ value: 77.003
1015
+ - type: ndcg_at_5
1016
+ value: 78.708
1017
+ - type: precision_at_1
1018
+ value: 64.60000000000001
1019
+ - type: precision_at_10
1020
+ value: 9.43
1021
+ - type: precision_at_100
1022
+ value: 0.997
1023
+ - type: precision_at_1000
1024
+ value: 0.1
1025
+ - type: precision_at_3
1026
+ value: 28.467
1027
+ - type: precision_at_5
1028
+ value: 17.9
1029
+ - type: recall_at_1
1030
+ value: 64.60000000000001
1031
+ - type: recall_at_10
1032
+ value: 94.3
1033
+ - type: recall_at_100
1034
+ value: 99.7
1035
+ - type: recall_at_1000
1036
+ value: 99.8
1037
+ - type: recall_at_3
1038
+ value: 85.39999999999999
1039
+ - type: recall_at_5
1040
+ value: 89.5
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: 89.36
1052
+ - type: ap
1053
+ value: 75.26507519569006
1054
+ - type: f1
1055
+ value: 87.89845508858562
1056
+ language:
1057
+ - zh
1058
+ license: mit
1059
+ ---
1060
+ <h2 align="left">ZPoint Large Embedding for Chinese</h2>
1061
+ **[2024-06-04]** release zpoint_large_embedding_zh, and upload model weight to huggingface
1062
+
1063
+ ```python
1064
+ from sentence_transformers import SentenceTransformer
1065
+ sentences1 = ["这个产品真垃圾"]
1066
+ sentences2 = ["我太喜欢这个产品了"]
1067
+ model = SentenceTransformer('iampanda/zpoint_large_embedding_zh')
1068
+ embeddings_1 = model.encode(sentences1, normalize_embeddings=True)
1069
+ embeddings_2 = model.encode(sentences2, normalize_embeddings=True)
1070
+ similarity = embeddings_1 @ embeddings_2.T
1071
+ print(similarity)
1072
+ ```