Amu commited on
Commit
707b360
1 Parent(s): 73a4df3

[init] model

Browse files
README.md CHANGED
@@ -1,3 +1,1058 @@
1
  ---
2
- license: apache-2.0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3
  ---
 
 
 
1
  ---
2
+ tags:
3
+ - mteb
4
+ model-index:
5
+ - name: tao-8k
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: 46.6327281304144
18
+ - type: cos_sim_spearman
19
+ value: 48.842454434123376
20
+ - type: euclidean_pearson
21
+ value: 46.94481399008005
22
+ - type: euclidean_spearman
23
+ value: 48.842454434123376
24
+ - type: manhattan_pearson
25
+ value: 46.89375935801324
26
+ - type: manhattan_spearman
27
+ value: 48.78990181105918
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: 51.29442837260785
39
+ - type: cos_sim_spearman
40
+ value: 52.652094634834
41
+ - type: euclidean_pearson
42
+ value: 54.86278112546793
43
+ - type: euclidean_spearman
44
+ value: 52.65209238258423
45
+ - type: manhattan_pearson
46
+ value: 54.8164800665497
47
+ - type: manhattan_spearman
48
+ value: 52.626711935726014
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: 41.51200000000001
60
+ - type: f1
61
+ value: 39.47955832883091
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: 63.27653562193512
73
+ - type: cos_sim_spearman
74
+ value: 65.37293598647585
75
+ - type: euclidean_pearson
76
+ value: 63.91367659963474
77
+ - type: euclidean_spearman
78
+ value: 65.37294637878077
79
+ - type: manhattan_pearson
80
+ value: 63.89671277983551
81
+ - type: manhattan_spearman
82
+ value: 65.35510625635355
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: 39.92148459596857
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: 36.7800929733979
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: 84.56370955233704
116
+ - type: mrr
117
+ value: 87.14396825396825
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: 85.4719112626303
129
+ - type: mrr
130
+ value: 88.25107142857142
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: 24.314
142
+ - type: map_at_10
143
+ value: 36.157000000000004
144
+ - type: map_at_100
145
+ value: 38.004
146
+ - type: map_at_1000
147
+ value: 38.129999999999995
148
+ - type: map_at_3
149
+ value: 32.141999999999996
150
+ - type: map_at_5
151
+ value: 34.414
152
+ - type: mrr_at_1
153
+ value: 37.384
154
+ - type: mrr_at_10
155
+ value: 45.261
156
+ - type: mrr_at_100
157
+ value: 46.271
158
+ - type: mrr_at_1000
159
+ value: 46.32
160
+ - type: mrr_at_3
161
+ value: 42.760999999999996
162
+ - type: mrr_at_5
163
+ value: 44.219
164
+ - type: ndcg_at_1
165
+ value: 37.384
166
+ - type: ndcg_at_10
167
+ value: 42.599
168
+ - type: ndcg_at_100
169
+ value: 50.068999999999996
170
+ - type: ndcg_at_1000
171
+ value: 52.221
172
+ - type: ndcg_at_3
173
+ value: 37.551
174
+ - type: ndcg_at_5
175
+ value: 39.711
176
+ - type: precision_at_1
177
+ value: 37.384
178
+ - type: precision_at_10
179
+ value: 9.532
180
+ - type: precision_at_100
181
+ value: 1.554
182
+ - type: precision_at_1000
183
+ value: 0.183
184
+ - type: precision_at_3
185
+ value: 21.205
186
+ - type: precision_at_5
187
+ value: 15.539
188
+ - type: recall_at_1
189
+ value: 24.314
190
+ - type: recall_at_10
191
+ value: 52.463
192
+ - type: recall_at_100
193
+ value: 83.86099999999999
194
+ - type: recall_at_1000
195
+ value: 98.17399999999999
196
+ - type: recall_at_3
197
+ value: 37.341
198
+ - type: recall_at_5
199
+ value: 43.952999999999996
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: 78.80938063740228
211
+ - type: cos_sim_ap
212
+ value: 87.42519095434638
213
+ - type: cos_sim_f1
214
+ value: 80.08597528210638
215
+ - type: cos_sim_precision
216
+ value: 74.10501193317423
217
+ - type: cos_sim_recall
218
+ value: 87.11713818096797
219
+ - type: dot_accuracy
220
+ value: 78.80938063740228
221
+ - type: dot_ap
222
+ value: 87.44023261310717
223
+ - type: dot_f1
224
+ value: 80.08597528210638
225
+ - type: dot_precision
226
+ value: 74.10501193317423
227
+ - type: dot_recall
228
+ value: 87.11713818096797
229
+ - type: euclidean_accuracy
230
+ value: 78.80938063740228
231
+ - type: euclidean_ap
232
+ value: 87.42517285949802
233
+ - type: euclidean_f1
234
+ value: 80.08597528210638
235
+ - type: euclidean_precision
236
+ value: 74.10501193317423
237
+ - type: euclidean_recall
238
+ value: 87.11713818096797
239
+ - type: manhattan_accuracy
240
+ value: 78.90559230306675
241
+ - type: manhattan_ap
242
+ value: 87.38730802838026
243
+ - type: manhattan_f1
244
+ value: 80.1043138107139
245
+ - type: manhattan_precision
246
+ value: 74.82744620381648
247
+ - type: manhattan_recall
248
+ value: 86.1819032031798
249
+ - type: max_accuracy
250
+ value: 78.90559230306675
251
+ - type: max_ap
252
+ value: 87.44023261310717
253
+ - type: max_f1
254
+ value: 80.1043138107139
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: 69.863
266
+ - type: map_at_10
267
+ value: 77.865
268
+ - type: map_at_100
269
+ value: 78.21900000000001
270
+ - type: map_at_1000
271
+ value: 78.22200000000001
272
+ - type: map_at_3
273
+ value: 76.335
274
+ - type: map_at_5
275
+ value: 77.179
276
+ - type: mrr_at_1
277
+ value: 70.074
278
+ - type: mrr_at_10
279
+ value: 77.89
280
+ - type: mrr_at_100
281
+ value: 78.235
282
+ - type: mrr_at_1000
283
+ value: 78.238
284
+ - type: mrr_at_3
285
+ value: 76.466
286
+ - type: mrr_at_5
287
+ value: 77.241
288
+ - type: ndcg_at_1
289
+ value: 70.074
290
+ - type: ndcg_at_10
291
+ value: 81.375
292
+ - type: ndcg_at_100
293
+ value: 82.918
294
+ - type: ndcg_at_1000
295
+ value: 83.019
296
+ - type: ndcg_at_3
297
+ value: 78.32000000000001
298
+ - type: ndcg_at_5
299
+ value: 79.824
300
+ - type: precision_at_1
301
+ value: 70.074
302
+ - type: precision_at_10
303
+ value: 9.325999999999999
304
+ - type: precision_at_100
305
+ value: 1.001
306
+ - type: precision_at_1000
307
+ value: 0.101
308
+ - type: precision_at_3
309
+ value: 28.17
310
+ - type: precision_at_5
311
+ value: 17.682000000000002
312
+ - type: recall_at_1
313
+ value: 69.863
314
+ - type: recall_at_10
315
+ value: 92.202
316
+ - type: recall_at_100
317
+ value: 99.05199999999999
318
+ - type: recall_at_1000
319
+ value: 99.895
320
+ - type: recall_at_3
321
+ value: 83.93
322
+ - type: recall_at_5
323
+ value: 87.566
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: 25.730999999999998
335
+ - type: map_at_10
336
+ value: 80.765
337
+ - type: map_at_100
338
+ value: 83.486
339
+ - type: map_at_1000
340
+ value: 83.521
341
+ - type: map_at_3
342
+ value: 55.745999999999995
343
+ - type: map_at_5
344
+ value: 70.473
345
+ - type: mrr_at_1
346
+ value: 89.55
347
+ - type: mrr_at_10
348
+ value: 93.028
349
+ - type: mrr_at_100
350
+ value: 93.093
351
+ - type: mrr_at_1000
352
+ value: 93.096
353
+ - type: mrr_at_3
354
+ value: 92.80000000000001
355
+ - type: mrr_at_5
356
+ value: 92.92200000000001
357
+ - type: ndcg_at_1
358
+ value: 89.55
359
+ - type: ndcg_at_10
360
+ value: 87.898
361
+ - type: ndcg_at_100
362
+ value: 90.366
363
+ - type: ndcg_at_1000
364
+ value: 90.715
365
+ - type: ndcg_at_3
366
+ value: 86.497
367
+ - type: ndcg_at_5
368
+ value: 85.533
369
+ - type: precision_at_1
370
+ value: 89.55
371
+ - type: precision_at_10
372
+ value: 42.305
373
+ - type: precision_at_100
374
+ value: 4.82
375
+ - type: precision_at_1000
376
+ value: 0.48900000000000005
377
+ - type: precision_at_3
378
+ value: 77.833
379
+ - type: precision_at_5
380
+ value: 65.81
381
+ - type: recall_at_1
382
+ value: 25.730999999999998
383
+ - type: recall_at_10
384
+ value: 89.409
385
+ - type: recall_at_100
386
+ value: 97.62100000000001
387
+ - type: recall_at_1000
388
+ value: 99.565
389
+ - type: recall_at_3
390
+ value: 58.298
391
+ - type: recall_at_5
392
+ value: 75.315
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: 49.6
404
+ - type: map_at_10
405
+ value: 59.34
406
+ - type: map_at_100
407
+ value: 59.894999999999996
408
+ - type: map_at_1000
409
+ value: 59.913000000000004
410
+ - type: map_at_3
411
+ value: 56.667
412
+ - type: map_at_5
413
+ value: 58.196999999999996
414
+ - type: mrr_at_1
415
+ value: 49.6
416
+ - type: mrr_at_10
417
+ value: 59.34
418
+ - type: mrr_at_100
419
+ value: 59.894999999999996
420
+ - type: mrr_at_1000
421
+ value: 59.913000000000004
422
+ - type: mrr_at_3
423
+ value: 56.667
424
+ - type: mrr_at_5
425
+ value: 58.196999999999996
426
+ - type: ndcg_at_1
427
+ value: 49.6
428
+ - type: ndcg_at_10
429
+ value: 64.461
430
+ - type: ndcg_at_100
431
+ value: 67.08800000000001
432
+ - type: ndcg_at_1000
433
+ value: 67.578
434
+ - type: ndcg_at_3
435
+ value: 58.962
436
+ - type: ndcg_at_5
437
+ value: 61.741
438
+ - type: precision_at_1
439
+ value: 49.6
440
+ - type: precision_at_10
441
+ value: 8.07
442
+ - type: precision_at_100
443
+ value: 0.928
444
+ - type: precision_at_1000
445
+ value: 0.097
446
+ - type: precision_at_3
447
+ value: 21.867
448
+ - type: precision_at_5
449
+ value: 14.48
450
+ - type: recall_at_1
451
+ value: 49.6
452
+ - type: recall_at_10
453
+ value: 80.7
454
+ - type: recall_at_100
455
+ value: 92.80000000000001
456
+ - type: recall_at_1000
457
+ value: 96.7
458
+ - type: recall_at_3
459
+ value: 65.60000000000001
460
+ - type: recall_at_5
461
+ value: 72.39999999999999
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: 47.44132358599462
473
+ - type: f1
474
+ value: 34.814352930577854
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: 86.43527204502813
486
+ - type: ap
487
+ value: 55.197728692877554
488
+ - type: f1
489
+ value: 81.22331922899193
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: 72.21054197899034
501
+ - type: cos_sim_spearman
502
+ value: 77.10172371889475
503
+ - type: euclidean_pearson
504
+ value: 76.15914782847307
505
+ - type: euclidean_spearman
506
+ value: 77.10173036795658
507
+ - type: manhattan_pearson
508
+ value: 76.16257390318928
509
+ - type: manhattan_spearman
510
+ value: 77.10538180843567
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: 26.968179320629726
522
+ - type: mrr
523
+ value: 25.664285714285718
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: 66.674
535
+ - type: map_at_10
536
+ value: 75.624
537
+ - type: map_at_100
538
+ value: 75.96199999999999
539
+ - type: map_at_1000
540
+ value: 75.973
541
+ - type: map_at_3
542
+ value: 73.9
543
+ - type: map_at_5
544
+ value: 75.007
545
+ - type: mrr_at_1
546
+ value: 68.89699999999999
547
+ - type: mrr_at_10
548
+ value: 76.212
549
+ - type: mrr_at_100
550
+ value: 76.506
551
+ - type: mrr_at_1000
552
+ value: 76.517
553
+ - type: mrr_at_3
554
+ value: 74.72999999999999
555
+ - type: mrr_at_5
556
+ value: 75.65899999999999
557
+ - type: ndcg_at_1
558
+ value: 68.89699999999999
559
+ - type: ndcg_at_10
560
+ value: 79.19
561
+ - type: ndcg_at_100
562
+ value: 80.681
563
+ - type: ndcg_at_1000
564
+ value: 80.97999999999999
565
+ - type: ndcg_at_3
566
+ value: 75.954
567
+ - type: ndcg_at_5
568
+ value: 77.792
569
+ - type: precision_at_1
570
+ value: 68.89699999999999
571
+ - type: precision_at_10
572
+ value: 9.519
573
+ - type: precision_at_100
574
+ value: 1.026
575
+ - type: precision_at_1000
576
+ value: 0.105
577
+ - type: precision_at_3
578
+ value: 28.548000000000002
579
+ - type: precision_at_5
580
+ value: 18.117
581
+ - type: recall_at_1
582
+ value: 66.674
583
+ - type: recall_at_10
584
+ value: 89.55499999999999
585
+ - type: recall_at_100
586
+ value: 96.26
587
+ - type: recall_at_1000
588
+ value: 98.598
589
+ - type: recall_at_3
590
+ value: 81.029
591
+ - type: recall_at_5
592
+ value: 85.37700000000001
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: 68.13718897108271
604
+ - type: f1
605
+ value: 66.00508413016382
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: 72.542030934768
617
+ - type: f1
618
+ value: 71.87970959109703
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: 51.2
630
+ - type: map_at_10
631
+ value: 57.211999999999996
632
+ - type: map_at_100
633
+ value: 57.74
634
+ - type: map_at_1000
635
+ value: 57.791000000000004
636
+ - type: map_at_3
637
+ value: 55.900000000000006
638
+ - type: map_at_5
639
+ value: 56.665
640
+ - type: mrr_at_1
641
+ value: 51.300000000000004
642
+ - type: mrr_at_10
643
+ value: 57.252
644
+ - type: mrr_at_100
645
+ value: 57.789
646
+ - type: mrr_at_1000
647
+ value: 57.84
648
+ - type: mrr_at_3
649
+ value: 55.95
650
+ - type: mrr_at_5
651
+ value: 56.715
652
+ - type: ndcg_at_1
653
+ value: 51.2
654
+ - type: ndcg_at_10
655
+ value: 59.998
656
+ - type: ndcg_at_100
657
+ value: 62.971999999999994
658
+ - type: ndcg_at_1000
659
+ value: 64.453
660
+ - type: ndcg_at_3
661
+ value: 57.321
662
+ - type: ndcg_at_5
663
+ value: 58.711
664
+ - type: precision_at_1
665
+ value: 51.2
666
+ - type: precision_at_10
667
+ value: 6.87
668
+ - type: precision_at_100
669
+ value: 0.835
670
+ - type: precision_at_1000
671
+ value: 0.095
672
+ - type: precision_at_3
673
+ value: 20.467
674
+ - type: precision_at_5
675
+ value: 12.959999999999999
676
+ - type: recall_at_1
677
+ value: 51.2
678
+ - type: recall_at_10
679
+ value: 68.7
680
+ - type: recall_at_100
681
+ value: 83.5
682
+ - type: recall_at_1000
683
+ value: 95.39999999999999
684
+ - type: recall_at_3
685
+ value: 61.4
686
+ - type: recall_at_5
687
+ value: 64.8
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: 73.33000000000001
699
+ - type: f1
700
+ value: 72.76740880461465
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: 75.09474824038982
712
+ - type: cos_sim_ap
713
+ value: 79.49093167837522
714
+ - type: cos_sim_f1
715
+ value: 77.762619372442
716
+ - type: cos_sim_precision
717
+ value: 68.29073482428115
718
+ - type: cos_sim_recall
719
+ value: 90.28511087645195
720
+ - type: dot_accuracy
721
+ value: 75.09474824038982
722
+ - type: dot_ap
723
+ value: 79.49093167837522
724
+ - type: dot_f1
725
+ value: 77.762619372442
726
+ - type: dot_precision
727
+ value: 68.29073482428115
728
+ - type: dot_recall
729
+ value: 90.28511087645195
730
+ - type: euclidean_accuracy
731
+ value: 75.09474824038982
732
+ - type: euclidean_ap
733
+ value: 79.49093167837522
734
+ - type: euclidean_f1
735
+ value: 77.762619372442
736
+ - type: euclidean_precision
737
+ value: 68.29073482428115
738
+ - type: euclidean_recall
739
+ value: 90.28511087645195
740
+ - type: manhattan_accuracy
741
+ value: 74.93232268543584
742
+ - type: manhattan_ap
743
+ value: 79.50256779527038
744
+ - type: manhattan_f1
745
+ value: 77.3749426342359
746
+ - type: manhattan_precision
747
+ value: 68.42532467532467
748
+ - type: manhattan_recall
749
+ value: 89.01795142555439
750
+ - type: max_accuracy
751
+ value: 75.09474824038982
752
+ - type: max_ap
753
+ value: 79.50256779527038
754
+ - type: max_f1
755
+ value: 77.762619372442
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: 91.71
767
+ - type: ap
768
+ value: 89.30664330630684
769
+ - type: f1
770
+ value: 91.69380669543091
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: 27.87844586552044
782
+ - type: cos_sim_spearman
783
+ value: 33.55828345961726
784
+ - type: euclidean_pearson
785
+ value: 34.008422591348754
786
+ - type: euclidean_spearman
787
+ value: 33.55828173553759
788
+ - type: manhattan_pearson
789
+ value: 33.97354762221951
790
+ - type: manhattan_spearman
791
+ value: 33.55061748217219
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: 37.16475906990342
803
+ - type: cos_sim_spearman
804
+ value: 39.02023124990304
805
+ - type: euclidean_pearson
806
+ value: 37.12905621621282
807
+ - type: euclidean_spearman
808
+ value: 39.02017798495793
809
+ - type: manhattan_pearson
810
+ value: 37.16400100601629
811
+ - type: manhattan_spearman
812
+ value: 39.027383935772335
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: 66.7431509369159
824
+ - type: cos_sim_spearman
825
+ value: 69.10355047922879
826
+ - type: euclidean_pearson
827
+ value: 67.48723360063258
828
+ - type: euclidean_spearman
829
+ value: 69.10355047922879
830
+ - type: manhattan_pearson
831
+ value: 67.55981324291854
832
+ - type: manhattan_spearman
833
+ value: 69.1816947077302
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: 78.27412453529412
845
+ - type: cos_sim_spearman
846
+ value: 78.74292565872022
847
+ - type: euclidean_pearson
848
+ value: 77.95359390335884
849
+ - type: euclidean_spearman
850
+ value: 78.7428438579602
851
+ - type: manhattan_pearson
852
+ value: 77.99252788851469
853
+ - type: manhattan_spearman
854
+ value: 78.80401873296358
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: 66.42334440897298
866
+ - type: mrr
867
+ value: 76.24570128209263
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: 27.323999999999998
879
+ - type: map_at_10
880
+ value: 76.752
881
+ - type: map_at_100
882
+ value: 80.39
883
+ - type: map_at_1000
884
+ value: 80.457
885
+ - type: map_at_3
886
+ value: 53.93
887
+ - type: map_at_5
888
+ value: 66.263
889
+ - type: mrr_at_1
890
+ value: 89.90899999999999
891
+ - type: mrr_at_10
892
+ value: 92.35
893
+ - type: mrr_at_100
894
+ value: 92.43599999999999
895
+ - type: mrr_at_1000
896
+ value: 92.44
897
+ - type: mrr_at_3
898
+ value: 91.92
899
+ - type: mrr_at_5
900
+ value: 92.192
901
+ - type: ndcg_at_1
902
+ value: 89.90899999999999
903
+ - type: ndcg_at_10
904
+ value: 84.352
905
+ - type: ndcg_at_100
906
+ value: 87.978
907
+ - type: ndcg_at_1000
908
+ value: 88.631
909
+ - type: ndcg_at_3
910
+ value: 85.845
911
+ - type: ndcg_at_5
912
+ value: 84.35000000000001
913
+ - type: precision_at_1
914
+ value: 89.90899999999999
915
+ - type: precision_at_10
916
+ value: 41.985
917
+ - type: precision_at_100
918
+ value: 5.007000000000001
919
+ - type: precision_at_1000
920
+ value: 0.516
921
+ - type: precision_at_3
922
+ value: 75.146
923
+ - type: precision_at_5
924
+ value: 62.92100000000001
925
+ - type: recall_at_1
926
+ value: 27.323999999999998
927
+ - type: recall_at_10
928
+ value: 83.221
929
+ - type: recall_at_100
930
+ value: 95.088
931
+ - type: recall_at_1000
932
+ value: 98.436
933
+ - type: recall_at_3
934
+ value: 55.58
935
+ - type: recall_at_5
936
+ value: 69.594
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: 50.453
948
+ - type: f1
949
+ value: 48.736715267813835
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: 59.153574405500706
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: 52.79421409479782
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: 56.699999999999996
983
+ - type: map_at_10
984
+ value: 66.834
985
+ - type: map_at_100
986
+ value: 67.313
987
+ - type: map_at_1000
988
+ value: 67.325
989
+ - type: map_at_3
990
+ value: 65.017
991
+ - type: map_at_5
992
+ value: 65.927
993
+ - type: mrr_at_1
994
+ value: 56.699999999999996
995
+ - type: mrr_at_10
996
+ value: 66.834
997
+ - type: mrr_at_100
998
+ value: 67.313
999
+ - type: mrr_at_1000
1000
+ value: 67.325
1001
+ - type: mrr_at_3
1002
+ value: 65.017
1003
+ - type: mrr_at_5
1004
+ value: 65.927
1005
+ - type: ndcg_at_1
1006
+ value: 56.699999999999996
1007
+ - type: ndcg_at_10
1008
+ value: 71.576
1009
+ - type: ndcg_at_100
1010
+ value: 73.79400000000001
1011
+ - type: ndcg_at_1000
1012
+ value: 74.08200000000001
1013
+ - type: ndcg_at_3
1014
+ value: 67.73400000000001
1015
+ - type: ndcg_at_5
1016
+ value: 69.378
1017
+ - type: precision_at_1
1018
+ value: 56.699999999999996
1019
+ - type: precision_at_10
1020
+ value: 8.64
1021
+ - type: precision_at_100
1022
+ value: 0.9650000000000001
1023
+ - type: precision_at_1000
1024
+ value: 0.099
1025
+ - type: precision_at_3
1026
+ value: 25.2
1027
+ - type: precision_at_5
1028
+ value: 15.920000000000002
1029
+ - type: recall_at_1
1030
+ value: 56.699999999999996
1031
+ - type: recall_at_10
1032
+ value: 86.4
1033
+ - type: recall_at_100
1034
+ value: 96.5
1035
+ - type: recall_at_1000
1036
+ value: 98.7
1037
+ - type: recall_at_3
1038
+ value: 75.6
1039
+ - type: recall_at_5
1040
+ value: 79.60000000000001
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: 86.83
1052
+ - type: ap
1053
+ value: 70.2908139255317
1054
+ - type: f1
1055
+ value: 85.19267443803346
1056
  ---
1057
+
1058
+ a try for emebdding model
added_tokens.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "[CLS]": 101,
3
+ "[MASK]": 103,
4
+ "[PAD]": 0,
5
+ "[SEP]": 102,
6
+ "[UNK]": 100
7
+ }
config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./model/tao-8k",
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 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b165a06efd456ce41f0678aebbf579751d5504bd1ce48198b611c1ae00058e8
3
+ size 666905321
special_tokens_map.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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]",
12
+ "sep_token": "[SEP]",
13
+ "unk_token": "[UNK]"
14
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "[PAD]",
46
+ "[UNK]",
47
+ "[CLS]",
48
+ "[SEP]",
49
+ "[MASK]"
50
+ ],
51
+ "clean_up_tokenization_spaces": true,
52
+ "cls_token": "[CLS]",
53
+ "do_lower_case": true,
54
+ "mask_token": "[MASK]",
55
+ "model_max_length": 8192,
56
+ "pad_token": "[PAD]",
57
+ "sep_token": "[SEP]",
58
+ "strip_accents": null,
59
+ "tokenize_chinese_chars": true,
60
+ "tokenizer_class": "BertTokenizer",
61
+ "unk_token": "[UNK]"
62
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff